US5677991A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Speech recognition system using arbitration between continuous speech and isolated word modules
Assignee: Nuance Communications Inc
•
Filing: 1995-06-30
•
Granted: 1997-10-14
•
Expires: 2015-06-30
Abstract
Abstract In the speech recognition system disclosed herein, an input utterance is submitted to both a large vocabulary isolated word speech recognition module and a small vocabulary continuous speech recognition module. The two recognition modules generate respective scores for identified large vocabulary models and for sequences of small vocabulary models. The score provided by the continuous speech recognizer is normalized on the basis of the length of the speech input utterance and an arbitration algorithm selects among the candidates identified by the recognition modules. Preferably, the competing scores from the two recognizers are scaled by a factor or factors empirically trained to minimize incursion by each of the vocabularies on correct results from the other vocabulary.
Inventors
- 👤 Dong Hsu
- 👤 Harley M. Rosnow
- 👤 Vladimir Sejnoha
- 👤 Brian H. Wilson
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 18:53
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/26; G10L15/22; G10L2015/223
Claims Analysis
Total Claims: 10
Claim 1
Independent Claim
146 words
A flexible speech recognition system comprising: an isolated word speech recognizer; accessible by said isolated word speech recognizer, a first vocabulary of respective models, said isolated word speech recognizer operating to compare speech input with at least a selected portion of said first vocabulary and to provide a plurality of scores indicating the degree of match of said speech input with identified ones of said models; a continuous speech recognizer; accessible by said continuous speech recognizer, a second vocabulary of respective models, said continuous speech recognizer operating to compare speech input to said second vocabulary of models and to provide a score indicating the degree of match of said speech input with an identified sequence of the respective models; an arbitration algorithm for selecting from among the models identified by said isolated word speech recognizer and the sequence of models identified by said continuous speech recognizer.
Claim 2
Dependent Claim
146 words
A flexible speech recognition system comprising: an isolated word speech recognizer; accessible by said isolated word speech recognizer, a first vocabulary of respective models, said isolated word speech recognizer operating to compare speech input with at least a selected portion of said first vocabulary and to provide a plurality of scores indicating the degree of match of said speech input with identified ones of said models; a continuous speech recognizer; accessible by said continuous speech recognizer, a second vocabulary of respective models, said continuous speech recognizer operating to compare speech input to said second vocabulary of models and to provide a score indicating the degree of match of said speech input with an identified sequence of the respective models; an arbitration algorithm for selecting from among the models identified by said isolated word speech recognizer and the sequence of models identified by said continuous speech recognizer.
Claim 3
Dependent Claim
40 words
A recognition system as set forth in claim 1 further comprising means for applying a relative scaling said recognizer scores by a factor empirically trained to minimize incursions by each of said vocabularies on correct results from the other vocabulary.
Claim 4
Dependent Claim
177 words
A flexible speech recognition system comprising: an isolated word speech recognizer; accessible by said isolated word speech recognizer, a first vocabulary of respective models numbering in excess of 5000, said isolated word speech recognizer operating to compare speech input with at least a selected portion of said first vocabulary and to provide a plurality of scores indicating the degree of match of said speech input with identified ones of said models; a continuous speech recognizer; accessible by said continuous speech recognizer, a second vocabulary of respective models numbering less than 2000, said continuous speech recognizer operating to compare speech input to said second vocabulary of models and to provide a score indicating the degree of match of said speech input with an identified sequence of the respective models; means for normalizing the score provided by said continuous speech recognizer on the basis of the length of the speech input; and an arbitration algorithm for selecting from among the models identified by said isolated word speech recognizer and the sequence of models identified by said continuous speech recognizer.
Claim 5
Dependent Claim
177 words
A flexible speech recognition system comprising: an isolated word speech recognizer; accessible by said isolated word speech recognizer, a first vocabulary of respective models numbering in excess of 5000, said isolated word speech recognizer operating to compare speech input with at least a selected portion of said first vocabulary and to provide a plurality of scores indicating the degree of match of said speech input with identified ones of said models; a continuous speech recognizer; accessible by said continuous speech recognizer, a second vocabulary of respective models numbering less than 2000, said continuous speech recognizer operating to compare speech input to said second vocabulary of models and to provide a score indicating the degree of match of said speech input with an identified sequence of the respective models; means for normalizing the score provided by said continuous speech recognizer on the basis of the length of the speech input; and an arbitration algorithm for selecting from among the models identified by said isolated word speech recognizer and the sequence of models identified by said continuous speech recognizer.
Claim 6
Dependent Claim
40 words
A recognition system as set forth in claim 3 further comprising means for applying a relative scaling said recognizer scores by a factor empirically trained to minimize incursions by each of said vocabularies on correct results from the other vocabulary.
Claim 7
Dependent Claim
190 words
A flexible speech recognition system comprising: an isolated word speech recognizer; accessible by said isolated word speech recognizer, a first vocabulary of respective models numbering in excess of 5000, said isolated word speech recognizer operating to compare speech input with at least a selected portion of said first vocabulary and to provide a score indicating the degree of match of said speech input with an identified one of said models; a continuous speech recognizer; accessible by said continuous speech recognizer, a second vocabulary of respective models numbering less than 2000, said continuous speech recognizer operating to compare speech input to said second vocabulary of models and to provide a score indicating the degree of match of said speech input with an identified sequence of the respective models; means for applying a relative scaling of said recognizer scores; an arbitration algorithm for choosing between the model identified by said isolated word speech recognizer and the sequence of models identified by said continuous speech recognizer, the relative scaling of said scores being by a factor empirically trained to minimize incursions by each of said vocabularies on correct results from the other vocabulary.
Claim 8
Dependent Claim
190 words
A flexible speech recognition system comprising: an isolated word speech recognizer; accessible by said isolated word speech recognizer, a first vocabulary of respective models numbering in excess of 5000, said isolated word speech recognizer operating to compare speech input with at least a selected portion of said first vocabulary and to provide a score indicating the degree of match of said speech input with an identified one of said models; a continuous speech recognizer; accessible by said continuous speech recognizer, a second vocabulary of respective models numbering less than 2000, said continuous speech recognizer operating to compare speech input to said second vocabulary of models and to provide a score indicating the degree of match of said speech input with an identified sequence of the respective models; means for applying a relative scaling of said recognizer scores; an arbitration algorithm for choosing between the model identified by said isolated word speech recognizer and the sequence of models identified by said continuous speech recognizer, the relative scaling of said scores being by a factor empirically trained to minimize incursions by each of said vocabularies on correct results from the other vocabulary.
Claim 9
Dependent Claim
32 words
A recognition system as set forth in claim 5 further comprising means for normalizing the score provided by said continuous speech recognizer on the basis of the length of the speech input.
Claim 10
Dependent Claim
67 words
A recognition system as set forth in claim 5 wherein said scaling factor is determined by applying, with a given factor, A. isolated word test data to both recognizers and counting the intrusions by CSR models on correct ISR translations, and B. continuous word test data to both recognizers and counting intrusions by ISR models on correct CSR translations, and then adjusting said factor to minimize intrusions.
References Cited (Backward Citations)
US4349700A
Cited
US4980918A
Cited
US4837831A
Cited
US4829576A
Cited
US5231670A
Cited
US5388183A
Cited
US5280563A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2000-10-13 | 2001-04-14 | 2001-10-14 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2004-10-13 | 2005-04-14 | 2005-10-14 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2008-10-13 | 2009-04-14 | 2009-10-14 | $7700.00 | Window Closed / Lapsed |