Keyword recognition system and method
First Claim
Patent Images
1. A method for recognizing an utterance as a keyword which activates a speaker dependent recognition system on a first plurality of vocabulary words, the method comprising the steps of:
- prior to recognition;
storing a set of keyword templates corresponding to a second plurality of keywords and a set of vocabulary templates corresponding to said first plurality of vocabulary words, anddefining said vocabulary templates also as filler templates;
performing keyword recognition on said utterance by matching the utterance against a set of keyword templates and against said filler templates; and
if said utterance is recognized as one of said keywords, activating said speaker dependent recognition system to match at least a second utterance to said vocabulary words.
5 Assignments
0 Petitions
Accused Products
Abstract
A keyword recognition system for speaker dependent, dynamic time warping (DTW) recognition systems uses all of the trained word templates in the system, (keyword and vocabulary), to determine if an utterance is a keyword utterance or not. The utterance is selected as the keyword if a keyword score indicates a significant match to the keyword template and if the keyword score indicates a better match than do the entirety of scores to the vocabulary word templates.
231 Citations
28 Claims
-
1. A method for recognizing an utterance as a keyword which activates a speaker dependent recognition system on a first plurality of vocabulary words, the method comprising the steps of:
-
prior to recognition; storing a set of keyword templates corresponding to a second plurality of keywords and a set of vocabulary templates corresponding to said first plurality of vocabulary words, and defining said vocabulary templates also as filler templates; performing keyword recognition on said utterance by matching the utterance against a set of keyword templates and against said filler templates; and if said utterance is recognized as one of said keywords, activating said speaker dependent recognition system to match at least a second utterance to said vocabulary words. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A system for recognizing an utterance as a keyword which activates a speaker dependent recognition system on a first plurality of vocabulary words, the system comprising:
-
a storage unit for storing a set of keyword templates corresponding to a second plurality of keywords and a set of vocabulary templates corresponding to said first plurality of vocabulary words; a keyword recognition unit for performing keyword recognition on said utterance using a set of keyword templates and a set of filler templates defined as said vocabulary templates. - View Dependent Claims (10, 11, 12, 13, 14)
-
-
15. A method for recognizing an utterance as a keyword which activates a speaker dependent recognition system on a first plurality of vocabulary words, the method comprising the steps of:
prior to recognition; storing a set of keyword templates corresponding to a second plurality of keywords and a set of vocabulary templates corresponding to said first plurality of vocabulary words; and defining said vocabulary templates also as filler templates, wherein said filler templates are divided into subsets and each subset is associated with a different keyword template; performing keyword recognition on said utterance using a set of keyword templates and said filler templates; and if said utterance is recognized as one of said keywords, activating said speaker dependent recognition system to match at least a second utterance to said vocabulary words of the subset associated with the recognized keyword. - View Dependent Claims (16, 17, 18, 19, 20, 21, 22)
-
23. A system for recognizing an utterance as a keyword which activates a speaker dependent recognition system on a plurality of vocabulary words, the system comprising:
-
a storage unit for storing a set of keyword templates corresponding to a second plurality of keywords and a set of vocabulary templates corresponding to said first plurality of vocabulary words; a keyword recognition unit for performing keyword recognition on said utterance using a set of keyword templates and a set of filler templates defined as said vocabulary templates, wherein said filler templates are divided into subsets and each subset is associated with a different keyword template, and for selecting the subset associated with the recognized keyword for use by said speaker dependent recognition system. - View Dependent Claims (24, 25, 26, 27, 28)
-
Specification