US6154722A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method and apparatus for a speech recognition system language model that integrates a finite state grammar probability and an N-gram probability
Assignee: Apple Inc
•
Filing: 1997-12-18
•
Granted: 2000-11-28
•
Expires: 2017-12-18
Abstract
Abstract A method and an apparatus for a speech recognition system that uses a language model based on an integrated finite state grammar probability and an n-gram probability are provided. According to one aspect of the invention, speech signals are received into a processor of a speech recognition system. The speech signals are processed using a speech recognition system hosting a language model. The language model is produced by integrating a finite state grammar probability and an n-gram probability. In the integration, the n-gram probability is modified based on information provided by the finite state grammar probability; thus, the finite state grammar probability is subordinate to the n-gram probability. The language model is used by a decoder along with at least one acoustic model to perform a hypothesis search on an acoustic sequence to provide a word sequence output. The word sequence generated is representative of the received speech signals.
Inventors
- 👤 Jerome R. Bellegarda
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 15:40
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/08; G10L15/18; G10L15/183; G10L15/19; G10L15/197; G10L15/193
Claims Analysis
Total Claims: 18
Claim 1
Independent Claim
118 words
A method for recognizing speech comprising: receiving speech signals into a processor; processing the received speech signals using a language model produced by integrating a finite state grammar probability and an n-gram probability with the finite state grammar probability being subordinated to the n-gram probability, wherein the language model comprises a probability that is specified by the equation ##EQU4## where, w q is the word about to be predicted, H q is the admissible history for this particular word, G is the probabilistic finite state grammar, S q is the present sentence up to w q , and V is the vocabulary to which w q belongs; and generating a word sequence representative of the received speech signals.
Claim 2
Independent Claim
118 words
A method for recognizing speech comprising: receiving speech signals into a processor; processing the received speech signals using a language model produced by integrating a finite state grammar probability and an n-gram probability with the finite state grammar probability being subordinated to the n-gram probability, wherein the language model comprises a probability that is specified by the equation ##EQU4## where, w q is the word about to be predicted, H q is the admissible history for this particular word, G is the probabilistic finite state grammar, S q is the present sentence up to w q , and V is the vocabulary to which w q belongs; and generating a word sequence representative of the received speech signals.
Claim 3
Dependent Claim
32 words
The method of claim 1, wherein the language model is used with at least one acoustic model to perform a hypothesis search on an acoustic sequence to provide a word sequence output.
Claim 4
Dependent Claim
37 words
The method of claim 2, wherein the at least one acoustic model is based on a hidden Markov model paradigm, wherein the at least one acoustic model comprises one model for each of at least one phonemes.
Claim 5
Independent Claim
128 words
An apparatus for speech recognition comprising: an input for receiving speech signals into a processor; a processor configured to recognize the received speech signals using a language model produced by integrating a finite state grammar paradigm and an n-gram paradigm, with the finite state grammar paradigm being subordinated to the n-gram paradigm, wherein the language model comprises a probability that is specified by the equation ##EQU5## where, w q is the word about to be predicted, H q is the admissible history for this particular word, G is the probabilistic finite state grammar, S q is the present sentence up to w q , and V is the vocabulary to which w q belongs; and an output for providing a word sequence representative of the received speech signals.
Claim 6
Independent Claim
128 words
An apparatus for speech recognition comprising: an input for receiving speech signals into a processor; a processor configured to recognize the received speech signals using a language model produced by integrating a finite state grammar paradigm and an n-gram paradigm, with the finite state grammar paradigm being subordinated to the n-gram paradigm, wherein the language model comprises a probability that is specified by the equation ##EQU5## where, w q is the word about to be predicted, H q is the admissible history for this particular word, G is the probabilistic finite state grammar, S q is the present sentence up to w q , and V is the vocabulary to which w q belongs; and an output for providing a word sequence representative of the received speech signals.
Claim 7
Dependent Claim
39 words
The apparatus of claim 4, wherein the processor is further configured to control a hypothesis search by a decoder, the decoder using inputs from the language model and from at least one acoustic model to execute the hypothesis search.
Claim 8
Dependent Claim
20 words
The apparatus of claim 5, wherein the at least one acoustic model is based on a hidden Markov model paradigm.
Claim 9
Dependent Claim
100 words
A speech recognition process comprising a statistical learning technique that uses a language model produced by integrating a finite state grammar probability and an n-gram probability with the finite state grammar probability being subordinated to the n-gram probability, wherein the language model comprises a probability that is specified by the equation ##EQU6## where, w q is the word about to be predicted, H q is the admissible history for this particular word, G is the probabilistic finite state grammar, S q is the present sentence up to w q , and V is the vocabulary to which w q belongs.
Claim 10
Dependent Claim
100 words
A speech recognition process comprising a statistical learning technique that uses a language model produced by integrating a finite state grammar probability and an n-gram probability with the finite state grammar probability being subordinated to the n-gram probability, wherein the language model comprises a probability that is specified by the equation ##EQU6## where, w q is the word about to be predicted, H q is the admissible history for this particular word, G is the probabilistic finite state grammar, S q is the present sentence up to w q , and V is the vocabulary to which w q belongs.
Claim 11
Dependent Claim
39 words
The process of claim 7, wherein at least one acoustic model is used, the at least one acoustic model used with the language model in executing a hypothesis search on an acoustic sequence to provide a word sequence output.
Claim 12
Dependent Claim
138 words
A computer readable medium containing executable instructions which, when executed in a processing system, causes the system to perform a method for recognizing speech comprising: receiving a speech signal into a processor; processing the received speech signal using a language model produced by integrating a finite state grammar probability and an n-gram probability with the finite state gammar probability being subordinated to the n-gram probability, wherein the language model comprises a probability that is specified by the equation ##EQU7## where, w q is the word about to be predicted, H q is the admissible history for this particular word, G is the probabilistic finite state grammar, S q is the present sentence up to w q , and V is the vocabulary to which w q belongs; and generating a word sequence representative of the received speech signal.
Claim 13
Dependent Claim
138 words
A computer readable medium containing executable instructions which, when executed in a processing system, causes the system to perform a method for recognizing speech comprising: receiving a speech signal into a processor; processing the received speech signal using a language model produced by integrating a finite state grammar probability and an n-gram probability with the finite state gammar probability being subordinated to the n-gram probability, wherein the language model comprises a probability that is specified by the equation ##EQU7## where, w q is the word about to be predicted, H q is the admissible history for this particular word, G is the probabilistic finite state grammar, S q is the present sentence up to w q , and V is the vocabulary to which w q belongs; and generating a word sequence representative of the received speech signal.
Claim 14
Dependent Claim
34 words
The computer readable medium of claim 9, wherein the language model is used with at least one acoustic model to perform a hypothesis search on an acoustic sequence to provide a word sequence output.
Claim 15
Independent Claim
99 words
A method for generating a language model for use in a speech recognition system comprising: integrating a finite state grammar probability and an n-gram probability with the finite state grammar probability being subordinated to the n-gram probability, wherein the language model comprises a probability that is specified by the equation ##EQU8## where, w q is the word about to be predicted, H q is the admissible history for this particular word, G is the probabilistic finite state grammar, S q is the present sentence up to w q , and V is the vocabulary to which w q belongs.
Claim 16
Independent Claim
99 words
A method for generating a language model for use in a speech recognition system comprising: integrating a finite state grammar probability and an n-gram probability with the finite state grammar probability being subordinated to the n-gram probability, wherein the language model comprises a probability that is specified by the equation ##EQU8## where, w q is the word about to be predicted, H q is the admissible history for this particular word, G is the probabilistic finite state grammar, S q is the present sentence up to w q , and V is the vocabulary to which w q belongs.
Claim 17
Dependent Claim
33 words
The method of claim 11, further comprising using the language model along with at least one acoustic model to perform a hypothesis search on an acoustic sequence to provide a word sequence output.
Claim 18
Dependent Claim
37 words
The method of claim 12, wherein the at least one acoustic model is based on a hidden Markov model paradigm, wherein the at least one acoustic model comprises one model for each of at least one phonemes.
References Cited (Backward Citations)
US5621859A
Cited
US5477448A
Cited
US5485372A
Cited
US5521816A
Cited
US5535121A
Cited
US5537317A
Cited
US5799269A
Cited
US5712957A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2003-11-28 | 2004-05-29 | 2004-11-28 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2007-11-28 | 2008-05-29 | 2008-11-28 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2011-11-28 | 2012-05-29 | 2012-11-28 | $7700.00 | Window Closed / Lapsed |