https://openvoice-tech.net/api.php?action=feedcontributions&feedformat=atom&user=Solyarisoftware 2026-05-12T04:00:05Z User contributions MediaWiki 1.43.1 https://openvoice-tech.net/index.php?title=Italien_phoneme_list_(it)&diff=2377 2022-03-27T17:30:00Z

<p>Solyarisoftware: table filled with some test words</p> <hr /> <div>{{Supported by eSpeak}}<br /> {{Phoneme list introduction}}<br /> {| class=&quot;wikitable&quot;<br /> |+<br /> !Italien written version<br /> !Spoken like<br /> !Phonemes<br /> |-<br /> |caffè<br /> |caffè<br /> |<br /> |-<br /> |thè<br /> |tè<br /> |<br /> |-<br /> |te<br /> |te<br /> |<br /> |-<br /> |solyaris<br /> |soliaris<br /> |<br /> |-<br /> |software<br /> |softuer<br /> |<br /> |-<br /> |trade-off<br /> |treid off<br /> |<br /> |}<br /> <br /> [[Category:Phoneme list]]</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Talk:Python&diff=2227 2022-01-12T08:26:55Z

<p>Solyarisoftware: </p> <hr /> <div>I propose to add, at the end, a statement like:<br /> <br /> Python is de facto the most common used programming language in natural language processing (NLP) vertical, also because the huge ecosystem of open-source packages (libraries), e.g. to develop machine learning / deep learning alghorithms ([[Tensorflow]], [[Pythorch]], etc.), speech recognition ([[Vosk]], [[Coqui]], etc.), sound processing, etc.--[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:25, 6 January 2022 (CET)<br /> :Sounding good to me [[User:Solyarisoftware|Solyarisoftware]]. Just pinging [[User:Digitalica|Digitalica]] as author. Could be added in my personal opinion.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 23:07, 6 January 2022 (CET)<br /> <br /> great idea, go ahead ;-)<br /> :I've added text as suggested by Giorgio. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 17:52, 7 January 2022 (CET)<br /> <br /> :thanks--[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 09:26, 12 January 2022 (CET)</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Talk:Python&diff=2207 2022-01-06T10:27:08Z

<p>Solyarisoftware: </p> <hr /> <div>I propose to add, at the end, a statement like:<br /> <br /> Python is de facto the most common used programming language in natural language processing (NLP) vertical, also because the huge ecosystem of open-source packages (libraries), e.g. to develop machine learning / deep learning alghorithms ([[Tensorflow]], [[Pythorch]], etc.), speech recognition ([[Vosk]], [[Coqui]], etc.), sound processing, etc.--[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:25, 6 January 2022 (CET)</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Talk:Python&diff=2206 2022-01-06T10:25:25Z

<p>Solyarisoftware: Created page with &quot;I propose to add, at the end, a statement like: Python is de facto the most common used programming language in natural language processing (NLP) vertical, also because the h...&quot;</p> <hr /> <div>I propose to add, at the end, a statement like:<br /> <br /> Python is de facto the most common used programming language in natural language processing (NLP) vertical, also because the huge ecosystem of open-source packages (libraries), e.g. to develop machine learning / deep learning alghorithms (Tensorflow, Pythorch, etc.), speech recognition (Vosk, Coqui, etc.), sound processing, etc.--[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:25, 6 January 2022 (CET)</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversational_Design&diff=2205 2022-01-05T17:54:31Z

<p>Solyarisoftware: Redirected page to Conversation Design</p> <hr /> <div>#REDIRECT [[Conversation Design]]</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversational_Design&diff=2204 2022-01-05T17:53:06Z

<p>Solyarisoftware: synonym redirection</p> <hr /> <div>&lt;nowiki&gt;#&lt;/nowiki&gt;REDIRECT [[Conversation Design]]</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=User_talk:Solyarisoftware&diff=2203 2022-01-05T17:47:01Z

<p>Solyarisoftware: /* Notification test */</p> <hr /> <div>== Thank you ==<br /> <br /> Just wanted to thank you for contributing helpful content here :-).--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 18:03, 7 December 2021 (CET)<br /> <br /> == Notification test ==<br /> <br /> Hi [[User:Solyarisoftware|Giorgio]],<br /> just testing - do you receive a mail notification about that entry? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 17:53, 5 January 2022 (CET)<br /> <br /> hi Thorsten, thanks for your great work; I'm just trying to help/share your seed. <br /> And yes, I received a mail notification about this entry.--[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 18:47, 5 January 2022 (CET)</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Initiative&diff=2120 2021-12-20T08:03:57Z

<p>Solyarisoftware: typo correction</p> <hr /> <div>''There is a systematic ambiguity with this word ['''initiative'''] in voice-interface design.'' <br /> <br /> #''the first utterance of a dialog pair; for instance, a question that puts &quot;reactive pressure&quot; on the following utterance to be an answer in response.''<br /> #''the flow-control of a dialogue. Whichever agent has control of the conversational flow has initiative.''<br /> <br /> ''Note that initiative is not just who is talking. In an interview, for instance, the interviewer usually maintains initiative. While both parties speak regularly, and the interviewee often speaks for longer duration, the interviewer controls the flows by setting the agenda, asking the questions, requesting elaborations, and so on.'' <br /> <br /> ''Speech systems can be '''fixed-initiative''', in which one agent maintains all the control, or '''mixed-initiative''', in which either agent can take control at any time.''<br /> <br /> '''''Initiative manager''' is a software module in some voice-interface designs that weights the initiative toward the system ore the user depending on the state of repair, the experience of the user, the requirements of interaction script, and the need for specific dialogue management acts.'' &lt;ref&gt;from page 534 of book &quot;Voice Interaction Design&quot; (Randy, Allen Harris). 2005&lt;/ref&gt;<br /> <br /> ---<br /> <br /> ''A '''directed dialogue''' is a fixed-initiative dialogue fixed on the system.''&lt;ref&gt;from page 528 of book &quot;Voice Interaction Design&quot; (Randy, Allen Harris). 2005&lt;/ref&gt; <br /> <br /> ---<br /> <br /> ''The system initiates, and closely directs, all interaction. Most systems deployed thus far used a directed-dialog strategy. A '''directed dialog''' fora travel planning might sound like this:'' <br /> <br /> &lt;code&gt;System: What's the departure city?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: Um, San Francisco&lt;/code&gt;<br /> <br /> &lt;code&gt;System: And the arrival city?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: I wanna go to New York&lt;/code&gt;<br /> <br /> &lt;code&gt;System Ok, what day you are living?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: Next Tuesday&lt;/code&gt;<br /> <br /> &lt;code&gt;System: Great. And what time do you want to go?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: Sometime after ten a.m.&lt;/code&gt;<br /> <br /> ''This directed-dialog is an example of form-filling. The caller is asked a series of directed questions as is the caller were filling out a form.''<br /> <br /> ''With a mixed-initiative dialog strategy, the same travel dialog might allow callers more flexibility in what they can say. First the initiative come from the caller. Depending on the caller's response, the system may then take initiative and prompt for missing information:''<br /> <br /> &lt;code&gt;System: What are travel plans?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: I wanna go to New York next Tuesday morning.&lt;/code&gt;<br /> <br /> &lt;code&gt;System: Ok, and what's the departure city?&lt;/code&gt;<br /> <br /> ''In this second example, the caller provides several pieces of information for the trip, and then the system takes the initiative and prompts for the rest. All mixed-initiative dialogs need to include back-off strategies to capture missing pieces of information.''&lt;ref&gt;froem pages 63-64 of book Voce User Interface Design, by Choen, Giangola, Balogh. 2004&lt;/ref&gt;<br /> <br /> ---<br /> <br /> In a human-machine interaction, '''mixed-initiative''' could be also considered as an alternation of flow-control initiative during time. <br /> <br /> By example let's consider an home automation voice assistant; the initiative could be triggered by a question or command that user ask to the conversational system. <br /> <br /> The user question: W''hat's the weather today?'' triggers a turn-taking directed-dialog initiated by the user request ('''reactive-mode/pull-mode'''). <br /> <br /> Beside, the system could be initiate a conversation with the user, by example when some relevant event happens, say some input sensors (light sensor) detect the ambient lighting is too dark; In this case the system could ask the user: ''You want me to turn on the lights?''<br /> <br /> In this case is the system that initiates a new conversation session, maybe unrelated from the previous conversation/topic ('''proactive-mode/push mode''').<br /> <br /> So mixed-initiative happens on a system able to be reactive to user requests and at the same time being proactive, initiating new conversations (dialog sessions) with the user. In that sense, the initiative manager is a dialog manager able to manage directed-dialog flows, by example managing dialog digressions, arbitrating system-initiated notification/dialogs with previous conversation initiated by user (to accomplish a task), etc.<br /> <br /> ==References==<br /> <br /> &lt;references /&gt;</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Notification&diff=2118 2021-12-19T18:38:09Z

<p>Solyarisoftware: notification definition</p> <hr /> <div>In a human-machine interaction system, by example a virtual assistant, a notification is a &quot;push&quot; message that informs the user about some relevant event, probably relevant for the user. It could be via text or voice.<br /> <br /> The notification could be a single-turn stand-alone message, or could initiate a new conversation with user. In this case the conversation is system-initiated (see [[Initiative]]). <br /> <br /> In a voice/voiceonly system, by example where interface devices are smartspeaker, voice notifications rise possible user experience issues. By example too much notifications are annoying and their interrupts of an active dialog have to managed with a smart dialog manager/initiative manager (see [[Initiative]]).<br /> <br /> Majority of voice virtual assistants do not manage voice notifications and/or mixed-initiative. Amazon Alexa proposed some ProactiveEvents API&lt;ref&gt;https://developer.amazon.com/it/blogs/alexa/post/bbf23596-766a-4e7c-8d74-cbfc234b6791/how-to-send-media-event-notifications-to-your-alexa-skill-customers&lt;/ref&gt; to manage 3rd party skills. Currently Amazon Echo Dot smartspeakers manage 1st party notification with a visual alert&lt;ref&gt;https://www.youtube.com/watch?v=DmnQO5np7cw&lt;/ref&gt;.</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Initiative&diff=2117 2021-12-19T18:16:02Z

<p>Solyarisoftware: better explanation of what is an initiative manager</p> <hr /> <div>''There is a systematic ambiguity with this word ['''mixed-initiative'''] in voice-interface design.'' <br /> <br /> # ''the first utterance of a dialog pair; for instance, a question that puts &quot;reactive pressure&quot; on the following utterance to be an answer in response.''<br /> # ''the flow-control of a dialogue. Whichever agent has control of the conversational flow has initiative.'' <br /> <br /> ''Note that initiative is not just who is talking. In an interview, for instance, the interviewer usually maintains initiative. While both parties speak regularly, and the interviewee often speaks for longer duration, the interviewer controls the flows by setting the agenda, asking the questions, requesting elaborations, and so on.'' <br /> <br /> ''Speech systems can be '''fixed-initiative''', in which one agent maintains all the control, or '''mixed-initiative''', in which either agent can take control at any time.''<br /> <br /> '''''Initiative manager''' is a software module in some voice-interface designs that weights the initiative toward the system ore the user depending on the state of repair, the experience of the user, the requirements of interaction script, and the need for specific dialogue management acts.'' &lt;ref&gt;from page 534 of book &quot;Voice Interaction Design&quot; (Randy, Allen Harris). 2005&lt;/ref&gt;<br /> <br /> ---<br /> <br /> ''A '''directed dialogue''' is a fixed-initiative dialogue fixed on the system.''&lt;ref&gt;from page 528 of book &quot;Voice Interaction Design&quot; (Randy, Allen Harris). 2005&lt;/ref&gt; <br /> <br /> ---<br /> <br /> ''The system initiates, and closely directs, all interaction. Most systems deployed thus far used a directed-dialog strategy. A '''directed dialog''' fora travel planning might sound like this:'' <br /> <br /> &lt;code&gt;System: What's the departure city?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: Um, San Francisco&lt;/code&gt;<br /> <br /> &lt;code&gt;System: And the arrival city?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: I wanna go to New York&lt;/code&gt;<br /> <br /> &lt;code&gt;System Ok, what day you are living?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: Next Tuesday&lt;/code&gt;<br /> <br /> &lt;code&gt;System: Great. And what time do you want to go?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: Sometime after ten a.m.&lt;/code&gt;<br /> <br /> ''This directed-dialog is an example of form-filling. The caller is asked a series of directed questions as is the caller were filling out a form.''<br /> <br /> ''With a mixed-initiative dialog strategy, the same travel dialog might allow callers more flexibility in what they can say. First the initiative come from the caller. Depending on the caller's response, the system may then take initiative and prompt for missing information:''<br /> <br /> &lt;code&gt;System: What are travel plans?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: I wanna go to New York next Tuesday morning.&lt;/code&gt;<br /> <br /> &lt;code&gt;System: Ok, and what's the departure city?&lt;/code&gt;<br /> <br /> ''In this second example, the caller provides several pieces of information for the trip, and then the system takes the initiative and prompts for the rest. All mixed-initiative dialogs need to include back-off strategies to capture missing pieces of information.''&lt;ref&gt;froem pages 63-64 of book Voce User Interface Design, by Choen, Giangola, Balogh. 2004&lt;/ref&gt;<br /> <br /> ---<br /> <br /> In a human-machine interaction, '''mixed-initiative''' could be also considered as an alternation of flow-control initiative during time. <br /> <br /> By example let's consider an home automation voice assistant; the initiative could be triggered by a question or command that user ask to the conversational system. <br /> <br /> The user question: W''hat's the weather today?'' triggers a turn-taking directed-dialog initiated by the user request ('''reactive-mode/pull-mode'''). <br /> <br /> Beside, the system could be initiate a conversation with the user, by example when some relevant event happens, say some input sensors (light sensor) detect the ambient lighting is too dark; In this case the system could ask the user: ''You want me to turn on the lights?''<br /> <br /> In this case is the system that initiates a new conversation session, maybe unrelated from the previous conversation/topic ('''proactive-mode/push mode''').<br /> <br /> So mixed-initiative happens on a system able to be reactive to user requests and at the same time being proactive, initiating new conversations (dialog sessions) with the user. In that sense, the initiative manager is a dialog manager able to manage directed-dialogs flows, by example managing dialog digressions, arbitrating system-initiated notification/dialogs with previous conversation initiated by user (to accomplish a task), etc.<br /> <br /> == References ==</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Initiative&diff=2113 2021-12-19T11:54:25Z

<p>Solyarisoftware: initiative, mixed-initiative, directed-dialog</p> <hr /> <div>''There is a systematic ambiguity with this word in voice-interface design.'' <br /> <br /> # ''the first utterance of a dialog pair; for instance, a question that puts &quot;reactive pressure&quot; on the following utterance to be an answer in response.''<br /> # ''the flow-control of a dialogue. Whichever agent has control of the conversational flow has initiative.'' <br /> <br /> ''Note that initiative is not just who is talking. Ina an interview, for instance, the interviewer usually maintains initiative. While both parties speak regularly, and the interviewee often speaks for longer duration, the interviewer controls the flows by setting the agenda, asking the questions, requesting elaborations, and so on.'' <br /> <br /> ''Speech systems can be '''fixed-initiative''', in which one agent maintains all the control, or '''mixed-initiative''', in which either agent can take control at any time.''<br /> <br /> ''Initiative manager is a software module in some voice-interface designs that weights the initiative toward the system ore the user depending on the state of repair, the experience of the user, the requirements of interaction script, and the need for specific dialogue management acts.'' &lt;ref&gt;from page 534 of book &quot;Voice Interaction Design&quot; (Randy, Allen Harris). 2005&lt;/ref&gt;<br /> <br /> ---<br /> <br /> ''A '''directed dialogue''' is a fixed-initiative dialogue fixed on the system.''&lt;ref&gt;from page 528 of book &quot;Voice Interaction Design&quot; (Randy, Allen Harris). 2005&lt;/ref&gt; <br /> <br /> ---<br /> <br /> ''The system initiates, and closely directs, all interaction. Most systems deployed thus far used a directed-dialog strategy. A directed dialog fora travel planning might sound like this:'' <br /> <br /> &lt;code&gt;System: What's the departure city?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: Um, San Francisco&lt;/code&gt;<br /> <br /> &lt;code&gt;System: And the arrival city?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: I wanna go to New York&lt;/code&gt;<br /> <br /> &lt;code&gt;System Ok, what day you are living?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: Next Tuesday&lt;/code&gt;<br /> <br /> &lt;code&gt;System: Great. And what time do you want to go?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: Sometime after ten a.m.&lt;/code&gt;<br /> <br /> ''This directed-dialog is an example of form-filling. The caller is asked a series of directed questions as is the caller were filling out a form.''<br /> <br /> ''With a mixed-initiative dialog strategy, the same travel dialog might allow callers more flexibility in what they can say. First the initiative come from the caller. Depending on the caller's response, the system may then take initiative and prompt for missing information:''<br /> <br /> &lt;code&gt;System: What are travel plans?&lt;/code&gt;<br /> <br /> &lt;code&gt;Caller: I wanna go to New York next Tuesday morning.&lt;/code&gt;<br /> <br /> &lt;code&gt;System: Ok, and what's the departure city?&lt;/code&gt;<br /> <br /> ''In this second example, the caller provides several pieces of information for the trip, and then the system takes the initiative and prompts for the rest. All mixed-initiative dialogs need to include back-off strategies to capture missing pieces of information.''&lt;ref&gt;froem pages 63-64 of book Voce User Interface Design, by Choen, Giangola, Balogh. 2004&lt;/ref&gt;<br /> <br /> ---<br /> <br /> In a human-machine interaction, '''mixed-initiative''' could be also considered as an alternation of flow-control initiative during time. By example let's consider an home automation voice assistant. The initiative could be triggered by a question or command that user ask to the conversational system. Say &quot;what's the weather today?&quot;, this trigger a turn-taking directed-dialogue initiated by a user request ('''reactive-mode/pull-mode'''). <br /> <br /> Also, the system could be initiate a conversation with the user, by example when some relevant event happens, say some input sensors (light sensor) detect it's too dark. In this case the system could ask the user &quot;do yo want I turn on the light?&quot;. In this case is the system that initiate a conversation session ('''proactive-mode/push mode''').</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Comparison_of_voice_assistants&diff=2112 2021-12-19T11:05:24Z

<p>Solyarisoftware: </p> <hr /> <div>There are lots of (open) voice assistants out there. Maybe we can make a comparison list of which assistants exists, in which points they're equal and which aspects differ.<br /> {| class=&quot;wikitable&quot;<br /> |+Comparison of available voice assistants<br /> !<br /> ![[Mycroft]] AI<br /> ![[SEPIA]]<br /> ![[Rhasspy]]<br /> ![[Leon]]<br /> ![[Genie]]<br /> |-<br /> |Target group<br /> |<br /> |Makers, tinkerers, smart-home enthusiasts,<br /> end-users via mobile app <br /> |<br /> |<br /> |anyone, private user or enterprise<br /> |-<br /> |License<br /> |<br /> |MIT<br /> |<br /> |<br /> |Apache 2.0<br /> https://github.com/stanford-oval/genie-toolkit/blob/master/LICENSE<br /> |-<br /> |Requires internet access<br /> |<br /> |100% offline is possible, but services<br /> like Wikipedia or news require internet<br /> |<br /> |<br /> |offline engines, but services like Thingtalk for web services, require internet<br /> |-<br /> |Offline STT<br /> |<br /> |via [[SEPIA Speech-To-Text Server|SEPIA STT]]<br /> |<br /> |<br /> |No<br /> |-<br /> |Offline TTS<br /> |<br /> |via SEPIA-Home<br /> |<br /> |<br /> |No<br /> |-<br /> |URL<br /> |<br /> |https://sepia-framework.github.io/<br /> |<br /> |<br /> |https://oval.cs.stanford.edu/<br /> https://github.com/stanford-oval<br /> <br /> https://github.com/stanford-oval/genie-toolkit<br /> <br /> |-<br /> |Comment<br /> |<br /> |Highly customizable. Modules can be distributed to<br /> multiple Raspberry Pis in home network.<br /> |<br /> |<br /> |Genie is one of the core technologies enabling the Stanford open Virtual Assistant architecture. See: https://oval.cs.stanford.edu/<br /> |-<br /> |Linux<br /> |<br /> |Yes<br /> |<br /> |<br /> |<br /> |-<br /> |Windows<br /> |<br /> |Yes<br /> |<br /> |<br /> |<br /> |-<br /> |Mac OS X<br /> |<br /> |Yes<br /> |<br /> |<br /> |<br /> |-<br /> |Raspberry Pi<br /> |<br /> |Yes<br /> |<br /> |<br /> |<br /> |-<br /> |Own hw product line<br /> |<br /> |No (maybe someday ^^)<br /> |<br /> |<br /> |No<br /> |-<br /> |...<br /> |<br /> |<br /> |<br /> |<br /> |<br /> |}<br /> <br /> [[Category:Open Voice Assistants]]</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Genie&diff=2078 2021-12-18T09:38:34Z

<p>Solyarisoftware: </p> <hr /> <div>Genie is an open-source toolkit for building conversational agents in a cost-effective fashion, and a privacy-preserving reference virtual assistant.<br /> <br /> Genie is built by the Stanford Open Virtual Assistant Lab (OVAL)&lt;ref name=&quot;:0&quot;&gt;https://oval.cs.stanford.edu/&lt;/ref&gt;.<br /> <br /> <br /> ''&quot;We have built the first &quot;browser&quot; to the World Wide Voice Web, our Genie open-source virtual assistant. To scale up cost-effectively, we have created a Pretrained Agent Generator that can produce transactional dialogue agents from just database schemas, API signatures, and a few samples of natural language utterances.''<br /> <br /> ''We are now ready to apply it to the WWW. The idea is to standardize on APIs and provide open pretrained agents that interface to the APIs. For example, restaurants provide a menu and an ordering API in the standardized format, and they get a voice agent for ordering food. We believe an open, decentralized voice web ([[WWvW]]) will surpass any proprietary walled gardens.''<br /> <br /> ''Decentralization of the voice web promotes equal opportunity, global inclusion and accessibility, and consumer privacy.&quot;'' cit.&lt;ref name=&quot;:0&quot; /&gt;<br /> <br /> Genie is a core component of the Stanford Open Virtual Assistant 2.0 Platform (previously called ''Almond)''.<br /> <br /> == References ==<br /> <br /> * https://wiki.genie.stanford.edu/en/getting-started/intro-genie<br /> <br /> * https://github.com/stanford-oval/genie-toolkit<br /> <br /> * https://oval.cs.stanford.edu/workshop/<br /> <br /> * https://convcomp.it/whither-almond-the-stanford-university-open-virtual-assistant-will-go-b4d66167e76c</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Genie&diff=2077 2021-12-18T09:36:02Z

<p>Solyarisoftware: genie definition</p> <hr /> <div>Genie is an open-source toolkit for building conversational agents in a cost-effective fashion, and a privacy-preserving reference virtual assistant.<br /> <br /> Genie is built by the Stanford Open Virtual Assistant Lab (OVAL)&lt;ref name=&quot;:0&quot;&gt;https://oval.cs.stanford.edu/&lt;/ref&gt;.<br /> <br /> <br /> ''&quot;We have built the first &quot;browser&quot; to the World Wide Voice Web, our Genie open-source virtual assistant. To scale up cost-effectively, we have created a Pretrained Agent Generator that can produce transactional dialogue agents from just database schemas, API signatures, and a few samples of natural language utterances.''<br /> <br /> ''We are now ready to apply it to the WWW. The idea is to standardize on APIs and provide open pretrained agents that interface to the APIs. For example, restaurants provide a menu and an ordering API in the standardized format, and they get a voice agent for ordering food. We believe an open, decentralized voice web ([[WWvW]]) will surpass any proprietary walled gardens.''<br /> <br /> ''Decentralization of the voice web promotes equal opportunity, global inclusion and accessibility, and consumer privacy.&quot;'' cit.&lt;ref name=&quot;:0&quot; /&gt;<br /> <br /> == References ==<br /> <br /> * https://wiki.genie.stanford.edu/en/getting-started/intro-genie<br /> <br /> * https://github.com/stanford-oval/genie-toolkit<br /> <br /> * https://oval.cs.stanford.edu/workshop/<br /> <br /> * https://convcomp.it/whither-almond-the-stanford-university-open-virtual-assistant-will-go-b4d66167e76c</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversational_Agent&diff=2072 2021-12-13T13:26:30Z

<p>Solyarisoftware: added paragraph &quot;The reason why the term agent&quot;</p> <hr /> <div>A ''conversational agent'', or ''conversational system'', or ''dialog system'', is a computer system (hardware+software platform) intended to converse with a human in a natural language.<br /> <br /> Let's see what wikipedia states for ''conversational agent''&lt;ref name=&quot;:0&quot;&gt;https://en.wikipedia.org/wiki/Dialogue_system&lt;/ref&gt;:<br /> <br /> ''&quot;A dialogue system, or conversational agent (CA), is a computer system intended to converse with a human. Dialogue systems employed one or more of text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel''.&quot;<br /> <br /> In common practice, conversational agent in an umbrella term generally used as synonym of [[chatbot]], but technically a chatbot is a specific kind of conversational system where the communication channel user interface (UI) is just text messages, exchanged on chat-based platforms (as [[instant-messaging]] mobile apps). <br /> <br /> == ''The reason why the term agent'' ==<br /> Especially in academic parlance, the term ''conversational agent'' is synonym of ''chatbot'', and the reason emphasis on the ''agent'' is maybe because conversational agents was considered software agents&lt;ref&gt;https://en.wikipedia.org/wiki/Software_agent&lt;/ref&gt;, special application of intelligent systems&lt;ref&gt;https://en.wikipedia.org/wiki/Intelligent_agent&lt;/ref&gt; and Multi-agent systems&lt;ref&gt;/https://en.wikipedia.org/wiki/Multi-agent_system&lt;/ref&gt; research topic.<br /> <br /> The term ''agent'' is so probably misleading, because assimilating any conversational system as a software agent that mediate between an end-user (e.g. a consumer of a business platform) and a business human operator counterpart. That use case is a specific use case and not always applicable/true. <br /> <br /> The agentive role of a conversational system is commonly related to a the specifica scenario when the conversational system really acts as intermediator, requiring a final conversation between the end-user and a human operator (that's commonly called: ''[[human-in-the-loop]]''). <br /> <br /> But there are many cases where the conversational system is not properly an agent, by example in pure [[command-and-control]] conversational systems that just execute automation commands to action (electro-mechanical) actuators, by example in [[home-automation]] or industrial automation realms.<br /> <br /> The concept of conversational agent is currently also a synonym of [https://openvoice-tech.net/Virtual_assistants virtual assistant], in the sense of a real agentive/automation technology that assists humans to solve real-life problems, in real-time, with reactive and proactive dialogs (so called [https://openvoice-tech.net/Mixed-initiative mixed-initiative]), between the end-user and the assistant. <br /> <br /> A concrete example of a conversational agent that's a true agent, in the sense that act on behalf of end-user, conversating and explating tasks with other humans, is ''Google Duplex''&lt;ref&gt;https://ai.googleblog.com/2018/05/duplex-ai-system-for-natural-conversation.html&lt;/ref&gt;.<br /> <br /> == References ==</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Voice_assistant&diff=2071 2021-12-13T13:18:52Z

<p>Solyarisoftware: voice assitant definition</p> <hr /> <div>A '''virtual assistant''' is defined by wikipedia in this way:<br /> <br /> ''An '''intelligent virtual assistant''' ('''IVA''') or '''intelligent personal assistant''' ('''IPA''') is a software agent that can perform tasks or services for an individual based on commands or questions. The term &quot;chatbot&quot; is sometimes used to refer to virtual assistants generally or specifically accessed by online chat. In some cases, online chat programs are exclusively for entertainment purposes. Some virtual assistants are able to interpret human speech and respond via synthesized voices. Users can ask their assistants questions, control home automation devices and media playback via voice, and manage other basic tasks such as email, to-do lists, and calendars with verbal commands. A similar concept, however with differences, lays under the dialogue systems.''&lt;ref&gt;https://en.wikipedia.org/wiki/Virtual_assistant&lt;/ref&gt;<br /> <br /> A '''voice assistant''' is so a special case of virtual assistant, where the human-computer interaction is mainly done via voice ([https://openvoice-tech.net/Voicefirst voicefirst]). <br /> <br /> [https://openvoice-tech.net/Smartspeakers Smartspeakers] are HW device terminals that enable humans to interact with a (voice) assistant.</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversational_Agent&diff=2070 2021-12-13T13:08:48Z

<p>Solyarisoftware: </p> <hr /> <div>A ''conversational agent'', or ''conversational system'', or ''dialog system'', is a computer system (hardware+software platform) intended to converse with a human in a natural language.<br /> <br /> Let's see what wikipedia states for ''conversational agent''&lt;ref name=&quot;:0&quot;&gt;https://en.wikipedia.org/wiki/Dialogue_system&lt;/ref&gt;:<br /> <br /> ''&quot;A dialogue system, or conversational agent (CA), is a computer system intended to converse with a human. Dialogue systems employed one or more of text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel''.&quot;<br /> <br /> In common practice, conversational agent in an umbrella term generally used as synonym of [[chatbot]], but technically a chatbot is a specific kind of conversational system where the communication channel user interface (UI) is just text messages, exchanged on chat-based platforms (as [[instant-messaging]] mobile apps). <br /> <br /> Especially in academic parlance, the term ''conversational agent'' is synonym of ''chatbot'', and the reason emphasis on the &quot;agent&quot; is maybe because conversational agents was considered software agents&lt;ref&gt;https://en.wikipedia.org/wiki/Software_agent&lt;/ref&gt;, special application of intelligent systems&lt;ref&gt;https://en.wikipedia.org/wiki/Intelligent_agent&lt;/ref&gt; and Multi-agent systems&lt;ref&gt;/https://en.wikipedia.org/wiki/Multi-agent_system&lt;/ref&gt; research.<br /> <br /> The term ''agent'' is so probably misleading, because assimilating any conversational system as a software agent that mediate between an end-user (e.g. a consumer of a business platform) and a business human operator counterpart. That use case is a specific use case and not always applicable. <br /> <br /> The agentive role of a conversational system is commonly related to a the specifica scenario when the conversational system really acts as intermediator, requiring a final conversation between the end-user and a human operator (that's commonly called: ''[[human-in-the-loop]]''). <br /> <br /> But there are many cases where the conversational system is not properly an agent, by example in pure [[command-and-control]] conversational systems that just execute automation commands to action (electro-mechanical) actuators, by example in [[home-automation]] or industrial automation realms.<br /> <br /> == References ==</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversational_Agent&diff=2069 2021-12-13T13:06:54Z

<p>Solyarisoftware: trying a better explanation of the meaning of the term &quot;agent&quot;</p> <hr /> <div>A ''conversational agent'', or ''conversational system'', or ''dialog system'', is a computer system (hardware+software platform) intended to converse with a human in a natural language.<br /> <br /> Let's see what wikipedia states for ''conversational agent''&lt;ref name=&quot;:0&quot;&gt;https://en.wikipedia.org/wiki/Dialogue_system&lt;/ref&gt;:<br /> <br /> ''&quot;A dialogue system, or conversational agent (CA), is a computer system intended to converse with a human. Dialogue systems employed one or more of text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel''.&quot;<br /> <br /> In common practice, conversational agent in an umbrella term generally used as synonym of [[chatbot]], but technically a chatbot is a specific kind of conversational system where the communication channel user interface (UI) is just text messages, exchanged on chat-based platforms (as [[instant-messaging]] mobile apps). <br /> <br /> Especially in academic parlance, the term ''conversational agent'' is synonym of ''chatbot'', and the reason emphasis on the &quot;agent&quot; is maybe because conversational agents was considered software agents&lt;ref name=&quot;:0&quot; /&gt;, special application of intelligent systems&lt;ref&gt;https://en.wikipedia.org/wiki/Intelligent_agent&lt;/ref&gt; and Multi-agent systems&lt;ref&gt;/https://en.wikipedia.org/wiki/Multi-agent_system&lt;/ref&gt; research.<br /> <br /> The term ''agent'' is so probably misleading, because assimilating any conversational system as a software agent that mediate between an end-user (e.g. a consumer of a business platform) and a business human operator counterpart. That use case is a specific use case and not always applicable. <br /> <br /> The agentive role of a conversational system is commonly related to a the specifica scenario when the conversational system really acts as intermediator, requiring a final conversation bettwen the end-user and a human operator (that's commonly called: ''[[human-in-the-loop]]''). <br /> <br /> But there are many cases where the conversational system is not properly an agent, by example in pure [[command-and-control]] conversational systems that just execute automation commands to action (electro-mechanical) actuators, by example in [[home-automation]] or industrial automation realms.</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversational_Agent&diff=2068 2021-12-13T08:56:57Z

<p>Solyarisoftware: Minor grammar corrections; the virtual assistant paragraph has been moved away</p> <hr /> <div>A ''conversational agent'', is a synonym of ''conversational system'', a computer system intended to converse with a human in a natural language.<br /> <br /> Let's see what wikipedia states for conversational agent:<br /> <br /> ''A dialogue system, or conversational agent (CA), is a computer system intended to converse with a human. Dialogue systems employed one or more of text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel.''&lt;ref&gt;https://en.wikipedia.org/wiki/Dialogue_system&lt;/ref&gt;.<br /> <br /> In common practice, conversational agent in an umbrella term generally used as synonym of [[chatbot]], but technically a chatbot is instead a conversational system that communicate just via texts, on chat-based platforms (as instant-messaging mobile apps). <br /> <br /> Especially in academic parlance, the term conversational agent was synonym of chatbot, and the reason emphasis on the &quot;agent&quot; was maybe because conversational agents was considered a special application in intelligent systems&lt;ref&gt;https://en.wikipedia.org/wiki/Intelligent_agent&lt;/ref&gt; or Multi-agent systems&lt;ref&gt;/https://en.wikipedia.org/wiki/Multi-agent_system&lt;/ref&gt; research.<br /> <br /> The term ''agent'' is probably misleading, because assimilating any conversational system as an agent that mediate between an end-user (e.g. a consumer of a business platform) and a business human operator. That's in general not true. Instead the agentive role is commonly related to a special case of conversational system that act as intermediator, requiring a final conversation with a human operator (that's commonly called, in customer service realms: ''human-in-the-loop''). But there are many cases where the conversational system is not properly an agent, by example in pure [[command-and-control]] conversational systems that just execute automation commands to action (electro-mechanical) actuators, by example in [[home-automation]] or industrial automation realms.</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversational_Agent&diff=2067 2021-12-12T13:34:43Z

<p>Solyarisoftware: </p> <hr /> <div>A ''conversational agent'', or better , a ''conversational system'', is a computer system intended to converse with a human in a natural langue.<br /> <br /> Let's see what wikipedia states for conversational agent:<br /> <br /> ''A dialogue system, or conversational agent (CA), is a computer system intended to converse with a human. Dialogue systems employed one or more of text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel.''&lt;ref&gt;https://en.wikipedia.org/wiki/Dialogue_system&lt;/ref&gt;.<br /> <br /> In common practice, conversational agent in an umbrella term generally used as synonym of chatbot, even if a chatbot is a conversational agent that communicate just via texts, on chat-based platforms (as instant-messaging mobile apps). <br /> <br /> Especially in academic parlance, the term conversational agent was synonym of chatbot, and the reason emphasis on the &quot;agent&quot; was maybe because conversational agents was considered a special application in intelligent systems&lt;ref&gt;https://en.wikipedia.org/wiki/Intelligent_agent&lt;/ref&gt; or Multi-agent systems&lt;ref&gt;/https://en.wikipedia.org/wiki/Multi-agent_system&lt;/ref&gt; research.<br /> <br /> The term &quot;agent&quot; is probably misleading, because assimilating any conversational system as an agent that mediate between an end-user (e.g. a consumer of a business platform) and a business human operator. That's in general not true. Instead the agentive role is commonly related to a special case of conversational system that act as intermediator, requiring a final conversation with a human operator (that's commonly called, in customer service realms: ''human-in-the-loop''). <br /> <br /> But there are many cases where the conversational system is not properly an agent, by example in pure [[command-and-control]] conversational systems that just execute automation commands to action (electro-mechanical) actuators, by example in [[home-automation]] or industrial automation realms. <br /> <br /> Nevertheless the concept of &quot;conversational agent&quot;, even if ambiguous, is currently an active area of research of [[virtual assistants]], in the sense of a real agentive/automation technology that assists humans to solve real-life problems, in real-time in a reactive and proactive way (co called [[mixed-initiative]]). [[Voice assistants]] are a special case of virtual assistants&lt;ref&gt;https://en.wikipedia.org/wiki/Virtual_assistant&lt;/ref&gt;, where the human-computer interaction is mainly done via voice ([[voicefirst]]). [[Smartspeakers]] are HW device terminals that enable humans to interact with a (voice) assistant.</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversational_Agent&diff=2066 2021-12-12T13:32:53Z

<p>Solyarisoftware: </p> <hr /> <div>A ''conversational agent'', or better , a ''conversational system'', is a computer system intended to converse with a human in a natural langue.<br /> <br /> Let's see what wikipedia states for conversational agent:<br /> <br /> ''A dialogue system, or conversational agent (CA), is a computer system intended to converse with a human. Dialogue systems employed one or more of text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel.''&lt;ref&gt;https://en.wikipedia.org/wiki/Dialogue_system&lt;/ref&gt;.<br /> <br /> In common practice, conversational agent in an umbrella term generally used as synonym of chatbot, even if a chatbot is a conversational agent that communicate just via texts, on chat-based platforms (as instant-messaging mobile apps). <br /> <br /> Especially in academic parlance, the term conversational agent was synonym of chatbot, and the reason emphasis on the &quot;agent&quot; was maybe because conversational agents was considered a special application in intelligent systems&lt;ref&gt;https://en.wikipedia.org/wiki/Intelligent_agent&lt;/ref&gt; / Multi-agent systems&lt;ref&gt;/https://en.wikipedia.org/wiki/Multi-agent_system&lt;/ref&gt; research.<br /> <br /> The term &quot;agent&quot; is probably misleading, because assimilating any conversational system as an agent that mediate between an end-user (e.g. a consumer of a business platform) and a business human operator. That's in general not true. Instead the agentive role is commonly related to a special case of conversational system that act as intermediator, requiring a final conversation with a human operator (that's commonly called, in customer service realms: ''human-in-the-loop''). <br /> <br /> But there are many cases where the conversational system is not properly an agent, by example in pure [[command-and-control]] conversational systems that just execute automation commands to action (electro-mechanical) actuators, by example in [[home-automation]] or industrial automation realms. <br /> <br /> Nevertheless the concept of &quot;conversational agent&quot;, even if ambiguous, is currently an active area of research of [[virtual assistants]], in the sense of a real agentive/automation technology that assists humans to solve real-life problems, in real-time in a reactive and proactive way (co called [[mixed-initiative]]). [[Voice assistants]] are a special case of virtual assistants&lt;ref&gt;https://en.wikipedia.org/wiki/Virtual_assistant&lt;/ref&gt;, where the human-computer interaction is mainly done via voice ([[voicefirst]]). [[Smartspeakers]] are HW device terminals that enable humans to interact with a (voice) assistant.</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversational_Agent&diff=2065 2021-12-12T13:27:30Z

<p>Solyarisoftware: </p> <hr /> <div>A ''conversational agent'', or better , a ''conversational system'', is a computer system intended to converse with a human in a natural langue.<br /> <br /> Let's see what wikipedia states for conversational agent:<br /> <br /> ''A dialogue system, or conversational agent (CA), is a computer system intended to converse with a human. Dialogue systems employed one or more of text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel.''&lt;ref&gt;https://en.wikipedia.org/wiki/Dialogue_system&lt;/ref&gt;.<br /> <br /> In common practice, conversational agent in an umbrella term generally used as synonym of chatbot, even if a chatbot is a conversational agent that communicate just via texts, on chat-based platforms (as instant-messaging mobile apps). <br /> <br /> Especially in academic parlance, the term conversational agent was synonym of chatbot, and the reason emphasis on the &quot;agent&quot; was maybe because conversational agents was considered an special application of intelligent systems&lt;ref&gt;https://en.wikipedia.org/wiki/Intelligent_agent&lt;/ref&gt; / Multi-agent systems&lt;ref&gt;/https://en.wikipedia.org/wiki/Multi-agent_system&lt;/ref&gt; research.<br /> <br /> The term &quot;agent&quot; is misleading, because assimilating any conversational system as an agent that mediate between an end-user (e.g. a consumer of a business platform) and a business operator. That's in general not true. Instead this is commonly referred as a special case of conversational system and the human operator intervention is called &quot;human-in-the-loop&quot;. There are many cases where the conversational system is not an agent, by example in pure command-and-control conversational systems that just execute automation commands to action (electro-mechanical) actuators, by example in home-automation or industrial realms. <br /> <br /> Nevertheless the concept of &quot;conversational agent&quot;, even if ambiguous, is currently an active area of research of virtual assistants, in the sense of a real agentive/automation technology that assists humans to solve real-life problems, in real-time in a reactive and proactive way (co called mixed-initiative). Voice assistants are a special case of virtual assistants&lt;ref&gt;https://en.wikipedia.org/wiki/Virtual_assistant&lt;/ref&gt;, where the human-computer interaction is mainly done via voice (voicefirst). Smartspeakers are HW device terminals that enable humans to interact with a (voice) assistant.</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversational_Agent&diff=2064 2021-12-12T11:08:46Z

<p>Solyarisoftware: Conversational Agent definition</p> <hr /> <div>A ''conversational agent'', or better , a ''conversational system'', is a computer system intended to converse with a human in a natural langue.<br /> <br /> Let's see what wikipedia states for conversational agent:<br /> <br /> ''A dialogue system, or conversational agent (CA), is a computer system intended to converse with a human. Dialogue systems employed one or more of text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel.''&lt;ref&gt;https://en.wikipedia.org/wiki/Dialogue_system&lt;/ref&gt;<br /> <br /> The wikipedia definition is pretty good but a bit updated, because even the voice interaction is not mentioned! <br /> <br /> In common practice, conversational agent in an umbrella term generally used as synonym of chatbot, even if a chatbot is a conversational agent that communicate just via texts, on chat-based platforms (as instant-messaging mobile apps). <br /> <br /> Especially in academic parlance, the term conversational agent was synonym of chatbot, and the reason emphasis on the &quot;agent&quot; was maybe because conversational agents was considered an special application of intelligent systems&lt;ref&gt;https://en.wikipedia.org/wiki/Intelligent_agent&lt;/ref&gt; / Multi-agent systems&lt;ref&gt;/https://en.wikipedia.org/wiki/Multi-agent_system&lt;/ref&gt; research.<br /> <br /> The term &quot;agent&quot; is misleading, because assimilating any conversational system as an agent that mediate between an end-user (e.g. a consumer of a business platform) and a business operator. That's in general not true. Instead this is commonly referred as a special case of conversational system and the human operator intervention is called &quot;human-in-the-loop&quot;. There are many cases where the conversational system is not an agent, by example in pure command-and-control conversational systems that just execute automation commands to action (electro-mechanical) actuators, by example in home-automation or industrial realms. <br /> <br /> Nevertheless the concept of &quot;conversational agent&quot;, even if ambiguous, is currently an active area of research of virtual assistants, in the sense of a real agentive/automation technology that assists humans to solve real-life problems, in real-time in a reactive and proactive way (co called mixed-initiative). Voice assistants are a special case of virtual assistants&lt;ref&gt;https://en.wikipedia.org/wiki/Virtual_assistant&lt;/ref&gt;, where the human-computer interaction is mainly done via voice (voicefirst). Smartspeakers are HW device terminals that enable humans to interact with a (voice) assistant.</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Talk:Conversation_Design&diff=2063 2021-12-12T10:22:51Z

<p>Solyarisoftware: </p> <hr /> <div>== Category ==<br /> <br /> Any idea for a category for that article [[User:Solyarisoftware‎|Solyarisoftware‎]]--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 18:33, 10 December 2021 (CET)<br /> <br /> :Short answer: following the classification in this wiki home page: open voice assistants -&gt; Voice (any, not only open) assistant -&gt; any assitant / conversational &quot;agent&quot; --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 10:36, 12 December 2021 (CET)<br /> <br /> ::I could rename the category &quot;Open Voice Assistants&quot; to &quot;Voice Assistants&quot;. Would &quot;conversational agent&quot; be a subcategory below &quot;Voice Assistants&quot; or just a page in that category. So do you expect lots of pages in &quot;conversational agent&quot;? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 10:56, 12 December 2021 (CET)<br /> <br /> :::Two topics to be discussed:<br /> <br /> ::: 1. '''Open voice Assistant or Voice Assistant?''' So a voice assistant is a voice-interfaced virtual assistant. Maybe an open voice assitant is an open assistant made by opensource+opendata enablers. Usually we ALSO tend to refer to an open voice assistant to on-prem/offline system... That's frankly a specific case (I could have a full open system but delivered as a cloud service...). It's all debatable :)<br /> <br /> ::: 2. '''What's a &quot;conversational agent&quot; and is this a subcategory of an &quot;assistant&quot; ?''' That's a good question! I'll try to create a definition asap. In short: ''conversational agent'' is an umbrella academic term for ''chatbot'' (nowadays also a ''voicebot'' or ''multimodal bot''). Not necessarly a conversational agent is an ''assistant''. Indeed an assistant is a special kind of chatbot that just &quot;assists&quot; the user. I'll give examples in the definition.--[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:22, 12 December 2021 (CET)<br /> <br /> :Long anwser/questions: What's a category here? There is an ontology of categories in the site? I'm asking because some concepts are maybe not precisely related to just a single category. By example the [[real-time-factor]] is commonly used in ASR (one category) but also valid sometime when reasoning about latency of a TTS (another category). --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 10:36, 12 December 2021 (CET)<br /> :: If you look at the category tree on the Mainpage i thought it's helpful finding relevant content. I've already added some pages to multiple categories. So for example i'd add TTS and STT category to [[real-time-factor]] because it's related to both categories. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 10:56, 12 December 2021 (CET)<br /> <br /> ::: ok. thanks--[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:22, 12 December 2021 (CET)</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Talk:Main_Page&diff=2062 2021-12-12T10:04:16Z

<p>Solyarisoftware: /* What infos on Mainpage? */</p> <hr /> <div>== What infos on Mainpage? ==<br /> I'm not sure which content is helpful on Mainpage. Any ideas? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 08:46, 20 October 2021 (CEST)<br /> <br /> That's really important because is the landing page for a new user; some thoughts about it here below.<br /> <br /> In the home page I'd clarify a sort of &quot;manifesto&quot;, let me point out what I understand s far:<br /> <br /> 1- Openness: Open-source + open-data<br /> The wiki is dedicated to open* stuff. open-source/open-data. Two things a are obviously related. I absolutely agree and I'd stress this point, even if some concepts are independent from the openness, by example the concept of [[Conversation Design|conversational design]], or some basic glossary. <br /> <br /> 2- the wiki as web &quot;communication&quot; pattern<br /> <br /> - An how-to page section?<br /> Yo conceived this repo as a wiki, just &quot;a la wikipedia&quot; in all communication / content management. That' fully fair and I appreciate <br /> totally it but maybe it's not so clear to everyone involved. In my opinion the process that bringing a person to edit an existing page, or &quot;worst&quot;, to create a new page, is not trivial. My modest suggestion is to help reader (future author) with all kind of notes / remind in the pages, by example explaining the way to update a content using the discussion panel, etc. <br /> So maybe an &quot;HOW TO&quot; section could help<br /> <br /> - Video links<br /> Why to not link video of your youtube channel https://www.youtube.com/channel/UCjqqTVVBTsxpm0iOhQ1fp9g/videos? <br /> --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:01, 12 December 2021 (CET)<br /> <br /> == General ideas on this wiki? ==<br /> <br /> What do you think? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 21:22, 1 November 2021 (CET)<br /> <br /> :This seems a really worthwhile initiative. Regarding the section for Voice related paper, maybe you already have thoughts on this, but I think it would be useful to recommend the kinds of detail desired (Title, Authors, DOI, source link(s), adding categories). Open links (eg Arxiv) would be preferred over those to non-free / subscription sites. Might also want to mention any preferences around pre-review/early access papers and handling updated versions and broken links. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:06, 12 November 2021 (CET)<br /> ::Hello [[User:Nmstoker|Nmstoker]], i'm thinking of adding standard infobox templates for papers with that kind of informations you mentioned.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> :Another general thought: where do you stand on inclusion of opinion/original information in the wiki? Wikipedia is firmly about referencing information from sources, so they avoid hosting original information and only include things that are backed by references. I'm guessing that there may be grounds for more flexibility here, but deciding where to draw the line is worth considering. In a similar way, deciding where the line is between sharing knowledge vs excess promotion might need judgement. The key open source players do not strike me as being likely to over promote but there could be firms that aren't so reasonable, so having some kind of policy on this might help. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:15, 12 November 2021 (CET)<br /> ::Copy'n Paste information from internetpages is not what i would prefer. Linking to sources seems is better. I'd hope that we can create a central knowledgebase for all open voice related projects and for that we have to add relevant information here. Over time we could vote some active users for being Admins here and help to control excessive promotion. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> == Logo ideas ==<br /> <br /> As i'm a technology enthusiast, but truely not a design-guy the OpenVoice-Tech logo is &quot;functional&quot;. If you have ideas for a more attractive logo please help me :-). --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 19:12, 14 November 2021 (CET)<br /> <br /> == Added box with newest 5 articles on Mainpage ==<br /> <br /> Based on an idea from a nice guy at Mycroft community i've added a box containing the newest 5 articles on the Mainpage.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:17, 16 November 2021 (CET)<br /> <br /> == Added &quot;Contribution&quot; box on Mainpage ==<br /> <br /> If you would like to contribute to this Wiki i've added a box showing requested but not yet created pages on the Mainpage as a starting point. What do you think on this [[User:Eltocino|Eltocino]], [[User:Nmstoker|Nmstoker]], [[User:Florian|Florian]]? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 16:58, 19 November 2021 (CET)</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Talk:Main_Page&diff=2061 2021-12-12T10:02:45Z

<p>Solyarisoftware: /* What infos on Mainpage? */</p> <hr /> <div>== What infos on Mainpage? ==<br /> I'm not sure which content is helpful on Mainpage. Any ideas? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 08:46, 20 October 2021 (CEST)<br /> <br /> That's really important because is the landing page for a new user; some thoughts about it here below.<br /> <br /> In the home page I'd clarify a sort of &quot;manifesto&quot;, let me point out what I understand s far:<br /> <br /> 1- Openness: Open-source + open-data<br /> The wiki is dedicated to open* stuff. open-source/open-data. Two things a are obviously related. I absolutely agree and I'd stress this point, even if some concepts are independent from the openness, by example the concept of [[Conversation Design|conversational design]], or some basic glossary. <br /> <br /> 2- the wiki as web &quot;communication&quot; pattern<br /> <br /> - An how-to page section?<br /> Yo conceived this repo as a wiki, just &quot;a la wikipedia&quot; in all communication / content management. That' fully fair and I appreciate <br /> totally it but maybe it's not so clear to everyone involved. In my opinion the process that bringing a person to edit an existing page, or &quot;worst&quot;, to create a new page, is not trivial. My modest suggestion is to help reader (future author) with all kind of notes / remind in the pages, maybe with an &quot;HOW TO&quot; section?<br /> <br /> - Video links<br /> Why to not link video of your youtube channel https://www.youtube.com/channel/UCjqqTVVBTsxpm0iOhQ1fp9g/videos? <br /> --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:01, 12 December 2021 (CET)<br /> <br /> == General ideas on this wiki? ==<br /> <br /> What do you think? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 21:22, 1 November 2021 (CET)<br /> <br /> :This seems a really worthwhile initiative. Regarding the section for Voice related paper, maybe you already have thoughts on this, but I think it would be useful to recommend the kinds of detail desired (Title, Authors, DOI, source link(s), adding categories). Open links (eg Arxiv) would be preferred over those to non-free / subscription sites. Might also want to mention any preferences around pre-review/early access papers and handling updated versions and broken links. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:06, 12 November 2021 (CET)<br /> ::Hello [[User:Nmstoker|Nmstoker]], i'm thinking of adding standard infobox templates for papers with that kind of informations you mentioned.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> :Another general thought: where do you stand on inclusion of opinion/original information in the wiki? Wikipedia is firmly about referencing information from sources, so they avoid hosting original information and only include things that are backed by references. I'm guessing that there may be grounds for more flexibility here, but deciding where to draw the line is worth considering. In a similar way, deciding where the line is between sharing knowledge vs excess promotion might need judgement. The key open source players do not strike me as being likely to over promote but there could be firms that aren't so reasonable, so having some kind of policy on this might help. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:15, 12 November 2021 (CET)<br /> ::Copy'n Paste information from internetpages is not what i would prefer. Linking to sources seems is better. I'd hope that we can create a central knowledgebase for all open voice related projects and for that we have to add relevant information here. Over time we could vote some active users for being Admins here and help to control excessive promotion. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> == Logo ideas ==<br /> <br /> As i'm a technology enthusiast, but truely not a design-guy the OpenVoice-Tech logo is &quot;functional&quot;. If you have ideas for a more attractive logo please help me :-). --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 19:12, 14 November 2021 (CET)<br /> <br /> == Added box with newest 5 articles on Mainpage ==<br /> <br /> Based on an idea from a nice guy at Mycroft community i've added a box containing the newest 5 articles on the Mainpage.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:17, 16 November 2021 (CET)<br /> <br /> == Added &quot;Contribution&quot; box on Mainpage ==<br /> <br /> If you would like to contribute to this Wiki i've added a box showing requested but not yet created pages on the Mainpage as a starting point. What do you think on this [[User:Eltocino|Eltocino]], [[User:Nmstoker|Nmstoker]], [[User:Florian|Florian]]? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 16:58, 19 November 2021 (CET)</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Talk:Main_Page&diff=2060 2021-12-12T10:02:26Z

<p>Solyarisoftware: /* What infos on Mainpage? */</p> <hr /> <div>== What infos on Mainpage? ==<br /> I'm not sure which content is helpful on Mainpage. Any ideas? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 08:46, 20 October 2021 (CEST)<br /> <br /> That's really important because is the landing page for a new user; some thoughts about it here below.<br /> <br /> In the home page I'd clarify a sort of &quot;manifesto&quot;, let me point out what I understand s far:<br /> <br /> 1- Openness: Open-source + open-data<br /> The wiki is dedicated to open* stuff. open-source/open-data. Two things a are obviously related. I absolutely agree and I'd stress this point, even if some concepts are independent from the openness, by example the concept of [[Conversation Design|conversational design]], or some basic glossary. <br /> <br /> 2- the wiki as web &quot;communication&quot; pattern<br /> <br /> - An how-to page section?<br /> Yo conceived this repo as a wiki, just &quot;a la wikipedia&quot; in all communication / content management. That' fully fair and I appreciate <br /> totally it but maybe it's not so clear to everyone involved. In my opinion the process that bringing a person to edit an existing page, or &quot;worst&quot;, to create a new page, is not trivial. My modest suggestion is to help reader (future author) with all kind of notes / remind in the pages, maybe with an &quot;HOW TO&quot; section?<br /> <br /> - Video links<br /> Why to not link video of your youtube channel https://www.youtube.com/channel/UCjqqTVVBTsxpm0iOhQ1fp9g/videos? <br /> <br /> --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 11:01, 12 December 2021 (CET)<br /> <br /> == General ideas on this wiki? ==<br /> <br /> What do you think? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 21:22, 1 November 2021 (CET)<br /> <br /> :This seems a really worthwhile initiative. Regarding the section for Voice related paper, maybe you already have thoughts on this, but I think it would be useful to recommend the kinds of detail desired (Title, Authors, DOI, source link(s), adding categories). Open links (eg Arxiv) would be preferred over those to non-free / subscription sites. Might also want to mention any preferences around pre-review/early access papers and handling updated versions and broken links. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:06, 12 November 2021 (CET)<br /> ::Hello [[User:Nmstoker|Nmstoker]], i'm thinking of adding standard infobox templates for papers with that kind of informations you mentioned.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> :Another general thought: where do you stand on inclusion of opinion/original information in the wiki? Wikipedia is firmly about referencing information from sources, so they avoid hosting original information and only include things that are backed by references. I'm guessing that there may be grounds for more flexibility here, but deciding where to draw the line is worth considering. In a similar way, deciding where the line is between sharing knowledge vs excess promotion might need judgement. The key open source players do not strike me as being likely to over promote but there could be firms that aren't so reasonable, so having some kind of policy on this might help. [[User:Nmstoker|Nmstoker]] ([[User talk:Nmstoker|talk]]) 14:15, 12 November 2021 (CET)<br /> ::Copy'n Paste information from internetpages is not what i would prefer. Linking to sources seems is better. I'd hope that we can create a central knowledgebase for all open voice related projects and for that we have to add relevant information here. Over time we could vote some active users for being Admins here and help to control excessive promotion. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 20:23, 12 November 2021 (CET)<br /> <br /> == Logo ideas ==<br /> <br /> As i'm a technology enthusiast, but truely not a design-guy the OpenVoice-Tech logo is &quot;functional&quot;. If you have ideas for a more attractive logo please help me :-). --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 19:12, 14 November 2021 (CET)<br /> <br /> == Added box with newest 5 articles on Mainpage ==<br /> <br /> Based on an idea from a nice guy at Mycroft community i've added a box containing the newest 5 articles on the Mainpage.--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 07:17, 16 November 2021 (CET)<br /> <br /> == Added &quot;Contribution&quot; box on Mainpage ==<br /> <br /> If you would like to contribute to this Wiki i've added a box showing requested but not yet created pages on the Mainpage as a starting point. What do you think on this [[User:Eltocino|Eltocino]], [[User:Nmstoker|Nmstoker]], [[User:Florian|Florian]]? --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 16:58, 19 November 2021 (CET)</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Talk:Conversation_Design&diff=2056 2021-12-12T09:36:43Z

<p>Solyarisoftware: </p> <hr /> <div>== Category ==<br /> <br /> Any idea for a category for that article [[User:Solyarisoftware‎|Solyarisoftware‎]]--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 18:33, 10 December 2021 (CET)<br /> <br /> Short answer: <br /> following the classification in this wiki home page: <br /> open voice assistants -&gt; Voice (any, not only open) assistant -&gt; any assitant / conversational &quot;agent&quot;<br /> <br /> Long anwser/questions:<br /> What's a category here? <br /> There is an ontology of categories in the site?<br /> <br /> I'm asking because some concepts are maybe not precisely related to just a single category. By example the [[real-time-factor]] is commonly used in ASR (one category) but also valid sometime when reasoning about latency of a TTS (another category).<br /> --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 10:36, 12 December 2021 (CET)</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Talk:OVT:What_is_OpenVoice-Tech_Wiki&diff=2055 2021-12-12T09:25:31Z

<p>Solyarisoftware: /* about contributes on the wiki */</p> <hr /> <div>== Our principles ==<br /> <br /> Thanks [[User:Solyarisoftware|Solyarisoftware]] for bringing this topic up. I've created this page as a collection for principals of OpenVoice-Tech Wiki. Maybe we can discuss and develop our principals here. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 12:59, 10 December 2021 (CET)<br /> <br /> == about contributes on the wiki ==<br /> <br /> Hi Thorsten, a minor duplication of the same subject here: https://openvoice-tech.net/index.php?title=OpenVoice-Tech_Wiki_talk:About<br /> <br /> Following your right suggestions, I guess the fair process is: ''If you disagree with a written content do not simply change it, but use &quot;Discussion&quot; page to discuss with original writer''<br /> <br /> thanks<br /> --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 13:34, 10 December 2021 (CET)<br /> : In case it's obvious wrong then it can be corrected, but if it's general disagreement it should be discussed before edited. Do you have additional ideas for &quot;contribution guidelines&quot;?--[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 18:20, 10 December 2021 (CET)<br /> <br /> It's clear and I agree. Maybe the entire process (discussion on disagreement/major correction) could be pointed out / put in evidence in the main page / guidelines page, because for me, at first glance wasn't so clear.--[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 10:25, 12 December 2021 (CET)</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Talk:OVT:What_is_OpenVoice-Tech_Wiki&diff=2050 2021-12-10T12:34:11Z

<p>Solyarisoftware: /* about contributes on the wiki */ new section</p> <hr /> <div>== Our principles ==<br /> <br /> Thanks [[User:Solyarisoftware|Solyarisoftware]] for bringing this topic up. I've created this page as a collection for principals of OpenVoice-Tech Wiki. Maybe we can discuss and develop our principals here. --[[User:Thorsten|Thorsten]] ([[User talk:Thorsten|talk]]) 12:59, 10 December 2021 (CET)<br /> <br /> == about contributes on the wiki ==<br /> <br /> Hi Thorsten, a minor duplication of the same subject here: https://openvoice-tech.net/index.php?title=OpenVoice-Tech_Wiki_talk:About<br /> <br /> Following your right suggestions, I guess the fair process is: ''If you disagree with a written content do not simply change it, but use &quot;Discussion&quot; page to discuss with original writer''<br /> <br /> thanks<br /> --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 13:34, 10 December 2021 (CET)</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversation_Design&diff=2046 2021-12-10T08:52:58Z

<p>Solyarisoftware: Conversation design definition</p> <hr /> <div>&quot;''Conversation design'' (''CxD'') is about defining the interactions between the user and a conversational agent, based on how people communicate in real life.&quot; [https://uxdesign.cc/intro-to-conversation-design-ce3bd30e4385 cit.]<br /> <br /> Designing a (human-to-machine) conversation is mainly related to the linguistics (pragmatics, psycholinguistics, sociolinguistics) and the authoring/screenwriting. [https://developers.google.com/assistant/conversation-design/what-is-conversation-design Google], with the famous CxD depth, lead by [https://developers.google.com/assistant/conversation-design/learn-about-conversation James Giangola] et al, people that conceived Google Assistant UX, contributed few years ago to divulgate concepts now became &quot;common sense&quot; as: Voice User Interfaces (VUI) best practices, Grice's Maxims, botpersona, persona, multimodal conversations. <br /> <br /> The ''conversation designer'' has a fundamental role in any enterprise team that build professional conversational agents/virtual agents.</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Open_Voice_Technology_Wiki_talk:About&diff=2045 2021-12-10T08:28:46Z

<p>Solyarisoftware: /* about contributes on the wiki */ new section</p> <hr /> <div>== about contributes on the wiki ==<br /> <br /> Hi Thorsten!<br /> <br /> Thanks for your initiative here and your work on Open German Voice Dataset (even if I don't know German language(ù)!<br /> I'll try to contribute the wiki and for sure I'll share on twitter and linkedin.<br /> <br /> My personal main concern, when by example writing on this wiki a definition of a concept, or a company/project, is that I'm naturally biased/opinionated on a technology or any tech solution. Also any definition I could add is for sure debatable. Even if I'm aware about the wiki/wikipedia-like common way to evolve/refine contents (with the continuous-delivery :) contribute of many people during time), my question is:<br /> <br /> In general, it's ok if I submit a definition that inevitably contains a personal bias/comment ? <br /> <br /> Thanks again<br /> <br /> respect<br /> <br /> giorgio --[[User:Solyarisoftware|Solyarisoftware]] ([[User talk:Solyarisoftware|talk]]) 09:28, 10 December 2021 (CET)</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Open_Voice_Technology_Wiki_talk:About&diff=2044 2021-12-10T08:28:26Z

<p>Solyarisoftware: Blanked the page</p> <hr /> <div></div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Open_Voice_Technology_Wiki_talk:About&diff=2043 2021-12-10T08:26:47Z

<p>Solyarisoftware: about contributes on the wiki</p> <hr /> <div>Hi Thorsten!<br /> <br /> Thanks for your initiative here and your work on Open German Voice Dataset (even if I don't know German language(ù)!<br /> I'll try to contribute the wiki and for sure I'll share on twitter and linkedin.<br /> <br /> My personal main concern, when by example writing on this wiki a definition of a concept, or a company/project, is that I'm naturally biased/opinionated on a technology or any tech solution. Also any definition I could add is for sure debatable. Even if I'm aware about the wiki/wikipedia-like common way to evolve/refine contents (with the continuous-delivery :) contribute of many people during time), my question is:<br /> <br /> In general, it's ok if I submit a definition that inevitably contains a personal bias/comment ? <br /> <br /> Thanks again<br /> respect<br /> giorgio</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Real-time-factor&diff=2042 2021-12-10T08:05:46Z

<p>Solyarisoftware: RTF definition</p> <hr /> <div>The ''real time factor'' (''RTF'') is a common metric of measuring the speed of an automatic speech recognition system (ASR) in the decoding phase (&quot;at run-time&quot;). It can also be used in other context where an audio or video signal is processed (usually automatically) at nearly constant rate. All in all RTF is a measure of the latency of any (audio) processing system, not only a speech recognition engine, but also a text-to-speech engine, a [[transcoding]] engine, etc.<br /> <br /> If it takes time f(d) to process an input of duration d , the real time factor is defined as: RTF = f(d)/d<br /> <br /> If, for example, it takes 8 hours of computation time to process a recording of duration 2 hours, the real time factor is 4. When the real time factor is 1, the processing is done &quot;in real time&quot;. It is a hardware dependent value, it is a network bandwidth dependent value (this is important to note, if processing is done as cloud-based service).<br /> <br /> Usually a state of the art speech-to-text cloud-based service supplied by Google, Azure, AWS, etc. has values between 0.2 and 0.6. Note that is all very depending on many factors, the network/internet bandwith, the speech content, etc. In case of an on-prem ASR, the major impacting factor is the algorithm and the hardware resources (CPU/RAM). &lt;syntaxhighlight lang=&quot;python&quot;&gt;<br /> def real_time_factor(processingTime, audioLenght, decimals=2):<br /> <br />     ''' Real-Time Factor (RTF) is defined as processing-time / length-of-audio. '''<br /> <br />     rtf = (processingTime / audioLenght)<br /> <br />     return round(rtf, decimals)<br /> &lt;/syntaxhighlight&gt;</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversational_AI&diff=2041 2021-12-10T07:41:11Z

<p>Solyarisoftware: </p> <hr /> <div>The term ''Conversational AI'', shortcut for ''Conversational Artificial Intelligence'' is an umbrella term, become spread in recent years, used to define all technologies around speech recognition (ASR), synthetic voice generation (TTS), natural language generation (NLG), dialog management (DM), chatbots, [[voicebots]], multimodal assistants in general.<br /> <br /> Not fully sure but the term has been probably &quot;coined&quot; in [[IBM Watson]] (TBV) and used as synonym of ''Conversational Computing'', another definition used at time in IBM, that doesn't gained success (TBV).</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=RASA&diff=2040 2021-12-10T07:38:15Z

<p>Solyarisoftware: </p> <hr /> <div>&quot;''Open source machine learning tools for developers to build, improve, and deploy text-and voice-based chatbots and assistants''&quot;. (cit. [https://github.com/RasaHQ/ RASA github home page]).<br /> <br /> RASA is probably the most important open-source tool to develop &quot;task-oriented&quot; conversational applications. Despite the RASA official statement, the original project has not conceived to manage voice interactions, but just [[chatbots]] with some support to GUI/buttons. <br /> <br /> RASA architecture consist in two main components: <br /> <br /> * ''RASA NLU'' is based upon [https://rasa.com/blog/introducing-dual-intent-and-entity-transformer-diet-state-of-the-art-performance-on-a-lightweight-architecture/ DIET algorithm], a a refined state of the art intent/entities &quot;classifier<br /> * ''RASA Core'' (now called ''RASA Dialog Manager''), based on [https://rasa.com/blog/unpacking-the-ted-policy-in-rasa-open-source/ TED policy], a machine learning algorithm, to manage multi-turn dialogs, escaping the traditional state-machine based way, but instead allowing conversation developers to insert &quot;''stories&quot;,'' set of of intents-actions sequences (conversation examples). With [https://rasa.com/blog/were-a-step-closer-to-getting-rid-of-intents/ end-to-end training], developers program the conversational agent [[dialog manager]] giving end-to-end turn-taking examples (the stories).<br /> <br /> RASA owned in few years now, a huge open community of developers and researchers. It's probably the biggest open source project to develop on-premise &quot;production-ready&quot; complex dialog systems. All the development ecosystem is around the [[Python]] programming language.<br /> <br /> == References ==<br /> <br /> * Home page: https://rasa.com/<br /> <br /> * Github: https://github.com/RasaHQ/<br /> <br /> * Community forum: https://forum.rasa.com/</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Glossary_of_voice_tech&diff=2037 2021-12-09T16:09:12Z

<p>Solyarisoftware: /* Voice assistant terms */</p> <hr /> <div>[[Category:Open Voice Tech]]<br /> <br /> In the field of voice technology there are lots of buzzwords. Some are self explaining, other lead to confusion regularly. This list should be a glossary.<br /> <br /> ==General terms==<br /> <br /> *[[:Category:Dataset|Dataset]]<br /> *[[Research papers|Papers]] (''research papers'')<br /> *[[Phonemes]]<br /> *[[Model]]<br /> *[[Checkpoint]]<br /> *[[Repository]]<br /> <br /> ==STT terms==<br /> <br /> *[[:Category:Wake words|Wake word]]<br /> *[[Hotword]]<br /> *[[Voice print]]<br /> *[[Word error rate]] (''WER'')<br /> *[[Diarization]]<br /> *[[Barge-in]]<br /> <br /> ==TTS terms==<br /> <br /> *<br /> <br /> ==Voice assistant terms==<br /> <br /> *[[Conversational AI]]<br /> *[[Natural language understanding]] (''NLU'')<br /> *[[Utterance]]<br /> *[[Voiceonly]]<br /> <br /> ==Machine learning==<br /> <br /> *[[Epoch]]<br /> *[[Step]]<br /> *[[Batch size]]<br /> *[[Learning rate]]<br /> *[[Inference]]<br /> *[[Alignment]]</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Conversational_AI&diff=2036 2021-12-09T16:07:34Z

<p>Solyarisoftware: definition of Conversational AI</p> <hr /> <div>The term ''Conversational AI'', shortcut for ''Conversational Artificial Intelligence'' is an umbrella term, become spread in recent years, used to define all technologies around speech recognition (ASR), synthetic voice generation (TTS), natural language generation (NLG), dialog management (DM), chatbots, voicebots, multimodal assistants in general.<br /> <br /> Not fully sure but the term has been probably &quot;coined&quot; in IBM (Watson) and used at times as synonym of ''Conversational Computing''. TBV.</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Glossary_of_voice_tech&diff=2035 2021-12-09T16:00:31Z

<p>Solyarisoftware: update of some keywords</p> <hr /> <div>[[Category:Open Voice Tech]]<br /> <br /> In the field of voice technology there are lots of buzzwords. Some are self explaining, other lead to confusion regularly. This list should be a glossary.<br /> <br /> ==General terms==<br /> <br /> *[[:Category:Dataset|Dataset]]<br /> *[[Research papers|Papers]] (''research papers'')<br /> *[[Phonemes]]<br /> *[[Model]]<br /> *[[Checkpoint]]<br /> *[[Repository]]<br /> <br /> ==STT terms==<br /> <br /> *[[:Category:Wake words|Wake word]]<br /> *[[Hotword]]<br /> *[[Voice print]]<br /> *[[Word error rate]] (''WER'')<br /> *[[Diarization]]<br /> *[[Barge-in]]<br /> <br /> ==TTS terms==<br /> <br /> *<br /> <br /> ==Voice assistant terms==<br /> <br /> *[[Utterance]]<br /> *[[Natural language understanding]] (''NLU'')<br /> *[[Voiceonly]]<br /> <br /> ==Machine learning==<br /> <br /> *[[Epoch]]<br /> *[[Step]]<br /> *[[Batch size]]<br /> *[[Learning rate]]<br /> *[[Inference]]<br /> *[[Alignment]]</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Natural_language_understanding&diff=2034 2021-12-09T15:55:49Z

<p>Solyarisoftware: DIET classifier link added</p> <hr /> <div>Natural Language Understanding (NLU) is a a misleading term, highly discussed in the Conversational AI / scientific community.<br /> <br /> In recent years, especially in the chatbot engineering industry, we tend to use NLU to mean an intent/entities classifier, based on machine learning techniques (transformers, etc.). The main open source project / state of the art of this approach is probably the [https://rasa.com/blog/introducing-dual-intent-and-entity-transformer-diet-state-of-the-art-performance-on-a-lightweight-architecture/ RASA DIET classifier].<br /> <br /> Besides, in terms of linguistic, and psycho-linguistic/cognitive scientific disciplines, there is a great skepticism about naming &quot;language understanding&quot; a ML-based classifier of intents (and entities). A growing number of researcher linguists state that it's even impossible to understand language with machine language techniques (the more famous and currently debated is probably GPT-3). One of the scientist more active in this battle is [https://ontologik.medium.com/ Walid Saba].</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Voiceonly&diff=2033 2021-12-09T15:53:41Z

<p>Solyarisoftware: voiceonly definition</p> <hr /> <div>A ''voiceonly'' (or ''voice-only'') application is, as the name suggests, a software application (like a voice-interfaced ''chatbot'', called also ''voicebot'' in this case) where the interface channel is only voice-based, without any graphical interface (GUI). <br /> <br /> In last years, a voiceonly channel is a synonym for using ''smartspeakers'', since when Amazon Echo device, terminal of the Amazon Alexa cloud-based system, was put on production in 2014; before, the traditional voice-only channel is of course the telephone and the IVR voice automation, still alive nowadays. <br /> <br /> To be precise, popular smartspeakers by Amazon and Google are example of so called ''voicefirst'' devices (not just voiceonly), because there users interact with virtual assistants primary via the voice channel (through the smartspeaker), but the users can also interact with the same assistants using the chat interface on a mobile phone app. <br /> <br /> Funny fact: the term voicefirst and especially the hashtag ''#voicefirst'' become popular few years ago on twitter, maybe used initially by [https://twitter.com/BrianRoemmele Brain Roemmele]. The term voicefirst become soon viral on voice / conversational AI community since then.<br /> <br /> Digression: the step forward the voicefirst conversational user experience (UX) is a ''multimodal'' conversational experience where the channel is not just the speech recognition or the texting (input) or the synthetic voice play or a written prompt (in output), but the conversation is true multimodal when really multi-sensory, where by example the input is not just text or voice but also gaze detection, gesture detection, geolocation info, ambient sensors, etc.</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=User:Solyarisoftware&diff=2032 2021-12-09T11:14:43Z

<p>Solyarisoftware: personal page</p> <hr /> <div>My name is Giorgio Robino. I'm from Genova, Italy. My nickname, solyarisoftware, is a tribute to Andrej Tarkovskij's movie SOLYARIS. <br /> <br /> I'm an engineer and researcher in &quot;Conversational AI&quot; verticals. I'm generally interested in voice/voiceonly multimodal interfaces (ASR/TTS) but I'm especially focused in dialog management and task-oriented realtime &quot;assistants&quot; that help human operator to complete real world working tasks. I call this kind of assistants: &quot;[https://docs.google.com/presentation/d/1ieZnAdREzEGXkcO4C_XPIbS9YAnE76mB0wpP2k-yOlQ/edit#slide=id.gc0058244ce_0_10 Enterpise Voice Cobots]&quot;. <br /> <br /> As Italian, I'm especially focused in the italian accademies and industries ecosystem (in natural language processing realms), and I realized in 2016 a first italian open conference #convcomp2016 about &quot;conversational computing&quot;. Afterward I maintained the related blog: [https://www.convcomp.it www.convcomp.it] where I try to share articles about topics related to chatbots/voicebots/virtual assistants. I'm also pretty active on [https://www.twitter.com/solyarisoftware twitter], where I share and chat/rant just only about conversational AI/voice related stuff.<br /> <br /> My current day job is &quot;Conversational AI Tech Lead&quot; in the Italian company [https://www.almawave.it www.almawave.it], where I'm now working in R%D projects, especially in ehealth realms.<br /> <br /> Of course I'm supporter of opensource and opendata also in voice realms. As free-time beside project, I published small open source projects:<br /> <br /> * https://github.com/solyarisoftware/naifjs, simple state-machine based dialog manager, in nodejs<br /> * https://github.com/solyarisoftware/voskJs, Vosk ASR offline engine API for NodeJs developers. With a simple HTTP ASR server<br /> * https://github.com/solyarisoftware/CoquiSTTJs, Coqui STT offline engine API for NodeJs developers. With a simple HTTP ASR server<br /> * https://github.com/solyarisoftware/jointts, a brainless concatenative text to speech<br /> * https://github.com/solyarisoftware/webad, Web Browser Audio Detection/Speech Recording Events API<br /> * https://github.com/solyarisoftware/Highlight.vim, Highlight vim plugin colorizes pattern of texts, with a random or specified background colors<br /> <br /> Last but not least, I have been an ambient music maker as [http://solyaris.altervista.org/ SOLYARIS MUSIC].</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Natural_language_understanding&diff=2025 2021-12-05T18:06:34Z

<p>Solyarisoftware: NLU definition</p> <hr /> <div>Natural Language Understanding (NLU) is a a misleading term, highly discussed in the Conversational AI / scientific community.<br /> <br /> In recent years, especially in the chatbot engineering industry, we tend to use NLU to mean an intent/entities classifier, based on machine learning techniques (transformers, etc.). The main open source project / state of the art of this approach is probably the RASA DIET classifier.<br /> <br /> Besides, in terms of linguistic, and psycho-linguistic/cognitive scientific disciplines, there is a great skepticism about naming &quot;language understanding&quot; a ML-based classifier of intents (and entities). A growing number of researcher linguists state that it's even impossible to understand language with machine language techniques (the more famous and currently debated is probably GPT-3). One of the scientist more active in this battle is [https://ontologik.medium.com/ Walid Saba].</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=RASA&diff=2022 2021-12-05T17:50:34Z

<p>Solyarisoftware: RASA platform description</p> <hr /> <div>Open source machine learning tools for developers to build, improve, and deploy text-and voice-based chatbots and assistants. (cit. RASA github home).<br /> <br /> RASA is probably the most important tool to develop &quot;task-oriented&quot; conversational application. Despite the RASA official statement, is not originally developed to manage voice interaction, but chatbots. RASA consist in two main components: <br /> <br /> * ''RASA NLU'' is based upon DIET, a a refined state of the art intent/entities classifier<br /> * ''RASA Core'' (now called ''RASA Dialog Manager''), based on TED, a machine learning algorithm, to manage multi-turn dialogs, escaping the traditional state-machine based way, but instead allowing conversation developers to insert &quot;''stories&quot;,'' set of sequences of intents-actions examples. In a sense, developers define the conversational agent dialog manager giving examples (the stories).<br /> <br /> RASA own a huge open community of developers and researchers. It's probably the biggest open source project to develop on-premise &quot;production-ready&quot; complex dialog systems. All the development ecosystem is around the Python programming language.<br /> <br /> == References ==<br /> home page: https://rasa.com/<br /> <br /> github: https://github.com/RasaHQ/<br /> <br /> community forum: https://forum.rasa.com/</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Diarization&diff=2017 2021-12-05T09:43:01Z

<p>Solyarisoftware: diarization definition minor correction</p> <hr /> <div>''Speaker diarisation'' (or ''diarization''), or s''peaker separation'' is the process of partitioning an input audio stream into homogeneous segments according to the speaker identity. It can enhance the readability of an automatic speech transcription by structuring the audio stream into speaker turns and, when used together with speaker recognition systems, by providing the speaker’s true identity.<br /> <br /> Source: https://en.wikipedia.org/wiki/Speaker_diarisation</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Barge-in&diff=2016 2021-12-05T09:41:57Z

<p>Solyarisoftware: barge-in definition</p> <hr /> <div>''&quot;Barge-in is a feature that allows callers to interrupt a prompt and provide their response before the prompt has finished playing&quot;'' at pag. 24 of book &quot;Voice User Interface Design&quot; by James Giangola et al.<br /> <br /> In other words, barge-in is, in any voice interface system / voice assistant, the user capability of interrupt/stop the assistant spoken (a text-to-speech synthetic voice play), to impose a new overriding user voice request to be processed asap.</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Diarization&diff=2015 2021-12-04T16:54:54Z

<p>Solyarisoftware: diarization new page</p> <hr /> <div>Speaker diarisation (or diarization), or Speaker separation is the process of partitioning an input audio stream into homogeneous segments according to the speaker identity. It can enhance the readability of an automatic speech transcription by structuring the audio stream into speaker turns and, when used together with speaker recognition systems, by providing the speaker’s true identity.<br /> <br /> Source: https://en.wikipedia.org/wiki/Speaker_diarisation</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Coqui&diff=2009 2021-12-03T17:27:57Z

<p>Solyarisoftware: introduced coaqui.ai description</p> <hr /> <div>[[Category:Coqui]]<br /> [[Category:Project]]<br /> <br /> <br /> https://coqui.ai/ Coqui is dedicated to open speech technology and to serving as the hub where speech researchers, developers, and practitioners congregate.<br /> <br /> https://github.com/coqui-ai/STT The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.<br /> <br /> https://github.com/coqui-ai/TTS 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production<br /> <br /> https://github.com/coqui-ai/snakepit 🐍 Coqui's machine learning job scheduler<br /> <br /> ---<br /> <br /> related projects:<br /> <br /> - https://github.com/solyarisoftware/CoquiSTTJs Coqui STT offline engine API for NodeJs developers. With a simple HTTP ASR server.<br /> <br /> == TTS ==<br /> Let's collect some questions related to Coqui TTS.<br /> <br /> * [[Continue Coqui TTS training based on checkpoint]]<br /> * [[Finetune existing Coqui TTS model]]</div>

Solyarisoftware https://openvoice-tech.net/index.php?title=Vosk&diff=2008 2021-12-03T17:08:45Z

<p>Solyarisoftware: </p> <hr /> <div>[https://github.com/alphacep/vosk-api Vosk] is an open-source speech recognition toolkit by Alphacephei&lt;ref&gt;https://alphacephei.com/vosk/&lt;/ref&gt;. Key features are:<br /> <br /> # Supports 20+ languages and dialects - English, Indian English, German, French, Spanish, Portuguese, Chinese, Russian, Turkish, Vietnamese, Italian, Dutch, Catalan, Arabic, Greek, Farsi, Filipino, Ukrainian, Kazakh, Swedish. More to come.<br /> # Works offline, even on lightweight devices - Raspberry Pi, Android, iOS<br /> # Installs with simple &lt;code&gt;pip3 install vosk&lt;/code&gt;<br /> # Portable per-language models are only 50Mb each, but there are much bigger server models available.<br /> # Provides streaming API for the best user experience (unlike popular speech-recognition python packages)<br /> # There are bindings for different programming languages, too - java/csharp/javascript etc.<br /> # Allows quick reconfiguration of vocabulary for best accuracy.<br /> # Supports speaker identification beside simple speech recognition.<br /> <br /> [[Category:STT]]<br /> &lt;references /&gt;Vosk related projects<br /> <br /> - https://github.com/solyarisoftware/voskjs Vosk ASR offline engine API for NodeJs developers. With a simple HTTP ASR server</div>

Solyarisoftware