A good wake word: Difference between revisions

Line 8:

If your wake word has a lot of rhyme potential, this is a sign it's probably going to have a lot of potential false activations. This can be partially mitigated with a quality dataset. The cadence of the wake word should also be as unique as possible. "Hey Mycroft" frequently has false activations when someone says "Microsoft". For these, finding cadence patterns and matching that to other phrases/words to build the dataset. The pronunciation of your wake word would ideally be smooth. Adding "hey" to the front of things is easy choice as the -ey phoneme leaves the mouth fairly neutral and ready to say another phoneme. Words like "axlotl" are definitely uncommon and unique, but not as smooth or easy to pronounce.

The accuracy of your listening engine in conjunction with your wake word should minimize false negatives for your target audience first, and minimize false positives second.

Revision as of 10:29, 10 November 2021 edit 72.128.154.254 (talk) No edit summary ← Older edit		Revision as of 10:38, 10 November 2021 edit undo 72.128.154.254 (talk) No edit summary Newer edit →
Line 8:		Line 8:

	If your wake word has a lot of rhyme potential, this is a sign it's probably going to have a lot of potential false activations. This can be partially mitigated with a quality dataset. The cadence of the wake word should also be as unique as possible. "Hey Mycroft" frequently has false activations when someone says "Microsoft". For these, finding cadence patterns and matching that to other phrases/words to build the dataset. The pronunciation of your wake word would ideally be smooth. Adding "hey" to the front of things is easy choice as the -ey phoneme leaves the mouth fairly neutral and ready to say another phoneme. Words like "axlotl" are definitely uncommon and unique, but not as smooth or easy to pronounce.		If your wake word has a lot of rhyme potential, this is a sign it's probably going to have a lot of potential false activations. This can be partially mitigated with a quality dataset. The cadence of the wake word should also be as unique as possible. "Hey Mycroft" frequently has false activations when someone says "Microsoft". For these, finding cadence patterns and matching that to other phrases/words to build the dataset. The pronunciation of your wake word would ideally be smooth. Adding "hey" to the front of things is easy choice as the -ey phoneme leaves the mouth fairly neutral and ready to say another phoneme. Words like "axlotl" are definitely uncommon and unique, but not as smooth or easy to pronounce.

			The accuracy of your listening engine in conjunction with your wake word should minimize false negatives for your target audience first, and minimize false positives second.