Registering and logging in removes this ad.
Registering and logging in removes this ad.
You say voice recognition, I say speech recogntion
Submitted by BruceCyr on Mon, 01/02/2006 - 14:27.
By way of arrogating pedantic prerogative, I note that the more precise usage is "speech recognition", although admittedly both terms are recognized.
"Voice recognition" more precisely refers to biometric applications, i.e., deducing the identity of a speaker based on characteristics of his/her voice.
"Speech recognition" refers to the inference of speech based on vocal utterances.
If all your SR software did was to tell you who is speaking based on your voice, you wouldn't find that useful. You want it to produce the text of what you say.
Alternatively, consider that coloraturas, mechanized garage doors and my hyper-vocal Irish Setter all have distinctive voices, but none of them are properly considered as producing speech. Formally, speech is a proper subset of all vocalizations.
Voice recognition has a role in speaker-specific speech recognition, namely during initialization when it learns and adapts to the sound of your voice from text(s) you read.
Bruce
PS: You might ask, "How is this an important distinction?". I don't know, but its unassailable as pure pedantry.
»
- BruceCyr's blog
- Login or register to post comments
