US6085160A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Language independent speech recognition
Assignee: Nuance Communications Inc
•
Filing: 1998-07-10
•
Granted: 2000-07-04
•
Expires: 2018-07-10
Abstract
Abstract A speech recognition system uses language independent acoustic models derived from speech data from multiple languages to represent speech units which are concatenated into words. In addition, the input speech signal which is compared to the language independent acoustic models may be vector quantized according to a codebook which is derived from speech data from multiple languages.
Inventors
- 👤 Bart D'hoore
- 👤 Dirk Van Compernolle
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 17:07
CPC Classifications
G; G09; G09B; G09B19/00; G09B19/06; G10; G10L; G10L15/00; G10L15/005; G10L15/08; G10L15/18
Claims Analysis
Total Claims: 28
Claim 1
Independent Claim
122 words
A language independent speech recognition system comprising: a. a speech pre-processor which receives input speech and produces a speech-related signal representative of the input speech; b. a database of acoustic hidden Markov models which represent subword units in each of a plurality of languages, wherein any subword unit that is common to two or more of the plurality of languages is represented by a single common acoustic hidden Markov model; c. a language model which characterizes a vocabulary of recognizable words and a set of grammar rules; and d. a speech recognizer which compares the speech-related signal to the acoustic hidden Markov models and the language model, and recognizes the input speech as a specific word sequence of at least one word.
Claim 2
Dependent Claim
122 words
A language independent speech recognition system comprising: a. a speech pre-processor which receives input speech and produces a speech-related signal representative of the input speech; b. a database of acoustic hidden Markov models which represent subword units in each of a plurality of languages, wherein any subword unit that is common to two or more of the plurality of languages is represented by a single common acoustic hidden Markov model; c. a language model which characterizes a vocabulary of recognizable words and a set of grammar rules; and d. a speech recognizer which compares the speech-related signal to the acoustic hidden Markov models and the language model, and recognizes the input speech as a specific word sequence of at least one word.
Claim 3
Dependent Claim
24 words
A system according to claim 1, wherein the speech pre-processor comprises a feature extractor which extracts relevant speech parameters to produce the speech-related signal.
Claim 4
Dependent Claim
41 words
A system according to claim 2, wherein the feature extractor includes a codebook created using speech data from the plurality of languages, and wherein the feature extractor uses vector quantization such that the speech-related signal is a sequence of feature vectors.
Claim 5
Dependent Claim
22 words
A system according to claim 1, wherein the acoustic hidden Markov models are created using speech data from the plurality of languages.
Claim 6
Dependent Claim
23 words
A system according to claim 1, wherein the subword units are at least one of phonemes, parts of phonemes, and sequences of phonemes.
Claim 7
Dependent Claim
19 words
A system according to claim 1, wherein the vocabulary of recognizable words contains words in the plurality of languages.
Claim 8
Dependent Claim
15 words
A system according to claim 1, wherein the vocabulary of recognizable words contains foreign-loan words.
Claim 9
Dependent Claim
20 words
A system according to claim 1, wherein the vocabulary of recognizable words contains proper names in the plurality of languages.
Claim 10
Dependent Claim
34 words
A system according to claim 1, wherein the words in the vocabulary of recognizable words are described by a voice print comprised of a user-trained sequence of acoustic hidden Markov models from the database.
Claim 11
Dependent Claim
28 words
A system according to claim 9, further comprising: e. a speaker identifier which uses the voice prints to determine the identity of the speaker of the speech input.
Claim 12
Dependent Claim
24 words
A system according to claim 1, wherein the vocabulary of recognizable words contains words in a language not present in the plurality of languages.
Claim 13
Dependent Claim
66 words
A system according to claim 1, wherein the speech recognizer compares the relevant speech parameters to acoustic models which represent subword units in a first language in the plurality of languages, and recognizes the speech input as a specific word sequence of at least one word in a second language in the plurality of languages so that input speech from a non-native speaker may be recognized.
Claim 14
Dependent Claim
49 words
A system according to claim 1, wherein the speech recognizer further provides an indication of how closely the input speech matches the words in the vocabulary of recognizable words, and if a specific pronunciation problem is present, assists a speaker of the input speech in correcting a pronunciation problem.
Claim 15
Independent Claim
123 words
A method of language independent speech recognition comprising: a. receiving input speech with a speech pre-processor and producing a speech-related signal representative of the input speech; b. representing in a database of acoustic hidden Markov models, subword units in each of a plurality of languages, wherein any subword unit that is common to two or more of the plurality of languages is represented by a single common acoustic hidden Markov model; c. characterizing in a language model a vocabulary of recognizable words and a set of grammar rules; and d. comparing in a speech recognizer the speech-related signal to the acoustic hidden Markov models and the language model, and recognizing the input speech as a specific word sequence of at least one word.
Claim 16
Independent Claim
123 words
A method of language independent speech recognition comprising: a. receiving input speech with a speech pre-processor and producing a speech-related signal representative of the input speech; b. representing in a database of acoustic hidden Markov models, subword units in each of a plurality of languages, wherein any subword unit that is common to two or more of the plurality of languages is represented by a single common acoustic hidden Markov model; c. characterizing in a language model a vocabulary of recognizable words and a set of grammar rules; and d. comparing in a speech recognizer the speech-related signal to the acoustic hidden Markov models and the language model, and recognizing the input speech as a specific word sequence of at least one word.
Claim 17
Dependent Claim
31 words
A method according to claim 14, wherein the step of receiving uses a speech pre-processor which further comprises a feature extractor for extracting relevant speech parameters and producing the speech-related signal.
Claim 18
Dependent Claim
41 words
A method according to claim 15, wherein the feature extractor includes a codebook created using speech data from the plurality of languages, and wherein the feature extractor uses vector quantization such that the speech-related signal is a sequence of feature vectors.
Claim 19
Dependent Claim
22 words
A method according to claim 14, wherein the acoustic hidden Markov models are created using speech data from the plurality of languages.
Claim 20
Dependent Claim
23 words
A method according to claim 14, wherein the subword units are at least one of phonemes, parts of phonemes, and sequences of phonemes.
Claim 21
Dependent Claim
19 words
A method according to claim 14, wherein the vocabulary of recognizable words contains words in the plurality of languages.
Claim 22
Dependent Claim
15 words
A method according to claim 14, wherein the vocabulary of recognizable words contains foreign-loan words.
Claim 23
Dependent Claim
20 words
A method according to claim 14, wherein the vocabulary of recognizable words contains proper names in the plurality of languages.
Claim 24
Dependent Claim
34 words
A method according to claim 14, wherein the words in the vocabulary of recognizable words are described by a voice print comprised of a user-trained sequence of acoustic hidden Markov models from the database.
Claim 25
Dependent Claim
28 words
A method according to claim 22, further comprising e. determining the identity of the speaker of the speech input with a speaker identifier which uses the voice prints.
Claim 26
Dependent Claim
24 words
A method according to claim 14, wherein the vocabulary of recognizable words contains words in a language not present in the plurality of languages.
Claim 27
Dependent Claim
68 words
A method according to claim 14, wherein the speech recognizer compares the relevant speech parameters to acoustic hidden Markov models which represent subword units in a first language in the plurality of languages, and recognizes the speech input as a specific word sequence of at least one word in a second language in the plurality of languages so that input speech from a non-native speaker may be recognized.
Claim 28
Dependent Claim
52 words
A method according to claim 14, wherein subpart (d) of the method further includes providing an indication of how closely the input speech matches the words in the vocabulary of recognizable words, and if a specific pronunciation problem is present, assists a speaker of the input speech in correcting a pronunciation problem.
References Cited (Backward Citations)
US5768603A
Cited
US5717743A
Cited
US5758023A
Cited
US5540589A
Cited
US5882202A
Cited
US5963892A
Cited
US5963903A
Cited
WO1998011534A1
Cited
US5915001A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2003-07-04 | 2004-01-03 | 2004-07-04 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2007-07-04 | 2008-01-03 | 2008-07-04 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2011-07-04 | 2012-01-03 | 2012-07-04 | $7700.00 | Window Closed / Lapsed |