US Patent No: 5,812,975

Number of patents in Portfolio can not be more than 2000

State transition model design method and voice recognition method and apparatus using same

Stats

ATTORNEY / AGENT: (SPONSORED)
 

Importance

Loading Importance Indicators... loading....

Abstract

A method of designing a state transition model capable of high speed voice recognition and a voice recognition method and apparatus using the state transition model is provided. The methods provide a state transition model in which a state shared structure of the state transition model is designed. The method includes a step of setting the states of a triphone state transition model in an acoustic space as initial clusters, a clustering step of generating a cluster containing the initial clusters by top-down clustering, a step of determining a state shared structure by assigning a short distance cluster among clusters generated by the clustering step, to the state transition model, and a step of learning a state shared model by analyzing the states of the triphones in accordance with the determined state shared structure.

Loading the Abstract Image... loading....

First Claim

Related Publications

Loading Related Publications... loading....

Patent Owner(s)

Patent OwnerAddressTotal Patents
CANON KABUSHIKI KAISHATOKYO49710

International Classification(s)

  • [Classification Symbol]
  • [Patents Count]

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
Komori, Yasuhiro Kawasaki, JP 70 533
Ohora, Yasunori Yokohama, JP 20 339

Cited Art

Patent Info (Count) # Cites Year
 
MATSUSHITA ELECTRIC INDUSTRIAL CO., LTD. (4)
5,307,444 Voice analyzing system using hidden Markov model and having plural neural network predictors 38 1990
5,444,817 Speech recognizing apparatus using the predicted duration of syllables 8 1992
5,608,841 Method and apparatus for pattern recognition employing the hidden Markov model 17 1993
5,638,489 Method and apparatus for pattern recognition employing the Hidden Markov Model 40 1995
 
INTERNATIONAL BUSINESS MACHINES CORPORATION (3)
4,817,156 Rapidly training a speech recognizer to a subsequent speaker given training data of a reference speaker 54 1987
5,165,007 Feneme-based Markov models for words 8 1989
5,050,215 Speech recognition method 57 1990
 
CANON KABUSHIKI KAISHA (2)
5,220,629 Speech synthesis apparatus and method 38 1990
5,381,514 Speech synthesizer and method for synthesizing speech for superposing and adding a waveform onto a waveform obtained by delaying a previously obtained waveform 13 1992
 
APPLE INC. (1)
5,535,305 Sub-partitioned vector quantization of probability density functions 35 1992
 
ITT CORPORATION (1)
5,073,939 Dynamic time warping (DTW) apparatus for use in speech recognition systems 19 1989
 
KABUSHIKI KAISHA TOSHIBA (1)
5,506,933 Speech recognition using continuous density hidden markov models and the orthogonalizing karhunen-loeve transformation 17 1993
 
RAMP HOLDINGS, INC. (F/K/A EVERYZING, INC.) (1)
5,621,859 Single tree method for grammar directed, very large vocabulary speech recognizer 91 1994
 
RICOH COMPANY, LTD. (1)
4,918,731 Speech recognition method and apparatus 11 1988
 
ROCKSTAR BIDCO, LP (1)
5,515,475 Speech recognition method using a two-pass search 42 1993
 
TTI INVENTIONS A LLC (1)
5,615,286 Method for determining a most likely sequence of states 5 1995

Patent Citation Ranking

Forward Cites

Patent Info (Count) # Cites Year
 
CANON KABUSHIKI KAISHA (12)
5,956,679 Speech processing apparatus and method using a noise-adaptive PMC model 33 1997
6,021,388 Speech synthesis apparatus and method 7 1997
6,236,962 Speech processing apparatus and method and computer readable medium encoded with a program for recognizing input speech by performing searches based on a normalized current feature parameter 9 1998
6,393,396 Method and apparatus for distinguishing speech from noise 5 1999
7,050,974 Environment adaptation for speech recognition in a speech communication system 5 2000
6,813,606 Client-server speech processing system, apparatus, method, and storage medium 14 2000
6,980,955 Synthesis unit selection apparatus and method, and storage medium 11 2001
7,054,814 Method and apparatus of selecting segments for speech synthesis by way of speech segment recognition 3 2001
7,039,588 Synthesis unit selection apparatus and method, and storage medium 11 2004
7,058,580 Client-server speech processing system, apparatus, method, and storage medium 5 2004
7,756,707 Signal processing apparatus and method 0 2005
7,565,290 Speech recognition method and apparatus 0 2005
 
MICROSOFT CORPORATION (8)
6,336,108 Speech recognition with mixtures of bayesian networks 46 1998
7,024,350 Compact easily parseable binary format for a context-free grammer 0 2001
7,634,406 System and method for identifying semantic intent from acoustic information 1 2004
7,283,959 Compact easily parseable binary format for a context-free grammar 2 2005
8,234,116 Calculating cost measures between HMM acoustic models 0 2006
8,244,534 HMM-based bilingual (Mandarin-English) TTS techniques 2 2007
7,571,096 Speech recognition using a state-and-transition based binary speech grammar with a last transition value 0 2007
8,060,360 Word-dependent transition models in HMM based word alignment for statistical machine translation 1 2007
 
AMERICAN TELEPHONE AND TELEGRAPH COMPANY, AT&T BELL LABORATORIES (7)
7,305,070 Sequential presentation of long instructions in an interactive voice response system 10 2002
7,526,731 Method for integrating user models to interface design 0 2006
7,907,719 Customer-centric interface and method of designing an interface 2 2006
7,453,994 Sequential presentation of long instructions in an interactive voice response system 2 2007
8,036,348 Sequential presentation of long instructions in an interactive voice response system 0 2008
7,836,405 Method for integrating user models to interface design 0 2009
8,103,961 Method for integrating user models to interface design 0 2010
 
MATSUSHITA ELECTRIC INDUSTRIAL CO., LTD. (4)
6,263,309 Maximum likelihood method for finding an adapted speaker model in eigenvoice space 14 1998
6,343,267 Dimensionality reduction for speaker normalization and speaker and environment adaptation using eigenvoice techniques 24 1998
6,571,208 Context-dependent acoustic models for medium and large vocabulary speech recognition with eigenvoice training 16 1999
6,526,379 Discriminative clustering methods for automatic speech recognition 15 1999
 
SBC TECHNOLOGY RESOURCES, INC. (4)
6,778,643 Interface and method of designing an interface 44 2000
7,086,007 Method for integrating user models to interface design 6 2000
6,853,966 Method for categorizing, describing and modeling types of system users 69 2002
7,076,049 Method of designing a telecommunications call center interface 21 2004
 
AT&T INTELLECTUAL PROPERTY I, L.P. (2)
7,751,552 Intelligently routing customer communications 1 2005
8,131,524 Method and system for automating the creation of customer-centric interfaces 1 2008
 
AT&T INTELLECTUAL PROPERTY II, L.P. (2)
7,587,320 Automatic segmentation in speech synthesis 6 2007
8,131,547 Automatic segmentation in speech synthesis 1 2009
 
AT&T KNOWLEDGE VENTURES, L.P. (2)
7,379,537 Method and system for automating the creation of customer-centric interfaces 5 2002
7,027,586 Intelligently routing customer communications 47 2003
 
SIVOX PARTNERS, LLC (2)
6,914,975 Interactive dialog-based training method 16 2002
8,023,636 Interactive dialog-based training method 0 2005
 
AT&T CORP. (1)
7,266,497 Automatic segmentation in speech synthesis 12 2003
 
INTELLECTUAL VENTURES FUND 83 LLC (1)
7,643,686 Multi-tiered image clustering by event 2 2005
 
INTERNATIONAL BUSINESS MACHINES CORPORATION (1)
6,073,096 Speaker adaptation system and method based on class-specific pre-clustering training speakers 41 1998
 
MITSUBISHI ELECTRIC RESEARCH LABORATORIES, INC. (1)
6,910,000 Generalized belief propagation for probabilistic systems 40 2000
 
PACIFIC BELL TELEPHONE COMPANY (1)
7,065,201 Telephone call processing in an interactive voice response call management system 26 2001
 
SBC TRI (1)
7,139,369 Interface and method of designing an interface 7 2002
 
TEXAS INSTRUMENTS INCORPORATED (1)
6,317,712 Method of phonetic modeling using acoustic decision tree 22 1999