US Patent No: 5,839,106

Number of patents in Portfolio can not be more than 2000

Large-vocabulary speech recognition using an integrated syntactic and semantic statistical language model

1 Status Updates

Stats

ATTORNEY / AGENT: (SPONSORED)

Importance

Loading Importance Indicators... loading....

Abstract

See full text

Methods and apparatus for performing large-vocabulary speech recognition employing an integrated syntactic and semantic statistical language model. In an exemplary embodiment, a stochastic language model is developed using a hybrid paradigm in which latent semantic analysis is combined with, and subordinated to, a conventional n-gram paradigm. The hybrid paradigm provides an estimate of the likelihood that a particular word, chosen from an underlying vocabulary will occur given a prevailing contextual history. The estimate is computed as a conditional probability that a word will occur given an 'integrated' history combining an n-word, syntactic-type history with a semantic-type history based on a much larger contextual framework. Thus, the exemplary embodiment seamlessly blends local language structures with global usage patterns to provide, in a single language model, the proficiency of a short-horizon, syntactic model with the large-span effectiveness of semantic analysis.

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

First Claim

See full text

Family

Loading Family data... loading....

Patent Owner(s)

Patent OwnerAddressTotal Patents
APPLE INC.CUPERTINO, CA15407

International Classification(s)

  • [Classification Symbol]
  • [Patents Count]

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
Bellegarda, Jerome R Los Gatos, CA 70 1703

Cited Art Landscape

Patent Info (Count) # Cites Year
 
APPLE INC. (1)
* 5,384,892 Dynamic language model for speech recognition 325 1992
 
CISCO TECHNOLOGY, INC. (1)
* 5,502,774 Automatic recognition of a consistent message using multiple complimentary sources of information 134 1994
* Cited By Examiner

Patent Citation Ranking

Forward Cite Landscape

Patent Info (Count) # Cites Year
 
Other [Check patent profile for assignment information] (2)
* 6,601,055 Explanation generation system for a diagnosis support tool employing an inference system 64 1999
8,977,584 Apparatuses, methods and systems for a digital conversation management platform 0 2011
 
Ramp, Inc. (1)
8,280,719 Methods and systems relating to information extraction 3 2006
 
NUANCE COMMUNICATIONS, INC. (35)
* 6,167,377 Speech recognition language models 99 1997
* 6,052,657 Text segmentation and identification of topic using language models 97 1997
* 6,996,519 Method and apparatus for performing relational speech recognition 7 2001
7,725,307 Query engine for processing voice based queries including semantic decoding 115 2003
9,076,448 Distributed real time speech recognition system 2 2003
7,555,431 Method for processing speech using dynamic grammars 118 2004
* 2004/0236,580 Method for processing speech using dynamic grammars 26 2004
* 8,036,893 Method and system for identifying and correcting accent-induced speech recognition difficulties 15 2004
* 7,640,159 System and method of speech recognition for non-native speakers of a language 6 2004
* 2006/0020,462 System and method of speech recognition for non-native speakers of a language 13 2004
* 2006/0020,463 Method and system for identifying and correcting accent-induced speech recognition difficulties 10 2004
7,308,404 Method and apparatus for speech recognition using a dynamic vocabulary 29 2004
* 2005/0055,210 Method and apparatus for speech recognition using a dynamic vocabulary 24 2004
7,729,904 Partial speech processing device and method for use in distributed systems 103 2004
7,702,508 System and method for natural language processing of query answers 96 2004
7,657,424 System and method for processing sentence based queries 113 2004
7,624,007 System and method for natural language processing of sentence based queries 96 2004
7,533,020 Method and apparatus for performing relational speech recognition 6 2005
* 2005/0234,723 Method and apparatus for performing relational speech recognition 19 2005
7,831,426 Network based interactive speech recognition system 110 2006
7,647,225 Adjustable resource based speech recognition system 94 2006
* 2007/0094,032 ADJUSTABLE RESOURCE BASED SPEECH RECOGNITION SYSTEM 2 2006
8,352,277 Method of interacting through speech with a web-connected server 10 2007
7,725,320 Internet based speech recognition system with dynamic grammars 96 2007
7,698,131 Speech recognition system for client devices having differing computing capabilities 87 2007
8,762,152 Speech recognition system interactive agent 0 2007
9,190,063 Multi-language speech recognition system 0 2007
7,912,702 Statistical language model trained with semantic variants 80 2007
7,873,519 Natural language speech lattice containing semantic variants 115 2007
* 2008/0052,063 Multi-language speech recognition system 73 2007
* 2008/0052,077 Multi-language speech recognition system 24 2007
7,672,841 Method for processing speech data for a distributed recognition system 83 2008
8,229,734 Semantic decoding of user queries 3 2008
7,725,321 Speech based query system using semantic decoding 84 2008
8,285,546 Method and system for identifying and correcting accent-induced speech recognition difficulties 11 2011
 
CXENSE ASA (2)
* 6,609,087 Fact recognition system 42 1999
* 2006/0253,274 Methods and systems relating to information extraction 18 2006
 
INTELLIGENT AUTOMATION, INC. (2)
7,062,220 Automated, computer-based reading tutoring systems and methods 20 2001
* 2002/0156,632 Automated, computer-based reading tutoring systems and methods 11 2001
 
MULTIMODAL TECHNOLOGIES, LLC (6)
7,584,103 Automated extraction of semantic content and generation of a structured document from speech 19 2004
* 2006/0041,428 Automated extraction of semantic content and generation of a structured document from speech 43 2004
8,560,314 Applying service levels to transcripts 0 2007
* 2007/0299,665 Automatic Decision Support 9 2007
8,321,199 Verification of extracted data 0 2010
* 2010/0211,869 Verification of Extracted Data 1 2010
 
APPLE INC. (61)
6,374,217 Fast update implementation for efficient latent semantic language modeling 35 1999
6,477,488 Method for dynamic context scope selection in hybrid n-gram+LSA language modeling 61 2000
6,697,779 Combined dual spectral and temporal alignment method for user authentication by voice 10 2000
* 6,778,952 Method for dynamic context scope selection in hybrid N-gram+LSA language modeling 59 2002
* 7,191,118 Method for dynamic context scope selection in hybrid N-gram+LSA language modeling 12 2004
* 2005/0015,239 Method for dynamic context scope selection in hybrid N-gramlanguage modeling 2 2004
8,677,377 Method and apparatus for building an intelligent automated assistant 17 2006
* 7,720,673 Method for dynamic context scope selection in hybrid N-GRAM+LSA language modeling 0 2007
* 2007/0162,276 Method for dynamic context scope selection in hybrid N-GRAMlanguage modeling 0 2007
8,977,255 Method and system for operating a multi-function portable electronic device using voice-activation 2 2007
8,645,137 Fast, language-independent method for user authentication by voice 9 2007
9,053,089 Part-of-speech tagging using latent analogy 0 2007
8,620,662 Context-aware unit selection 4 2007
9,330,720 Methods and apparatus for altering audio output signals 0 2008
8,996,376 Intelligent text-to-speech conversion 0 2008
8,768,702 Multi-tiered voice feedback in an electronic device 0 2008
8,898,568 Audio user interface 12 2008
8,712,776 Systems and methods for selective text to speech synthesis 3 2008
8,583,418 Systems and methods of detecting language and natural language strings for text to speech synthesis 2 2008
8,676,904 Electronic devices with voice command and contextual data processing capabilities 3 2008
8,862,252 Audio user interface for displayless electronic device 0 2009
8,614,431 Automated response to and sensing of user activity in portable devices 6 2009
8,682,649 Sentiment prediction from textual data 7 2009
8,600,743 Noise profile determination for voice-related feature 1 2010
8,682,667 User profiling for selecting user specific voice input processing information 12 2010
8,713,021 Unsupervised document clustering using latent semantic density analysis 1 2010
8,719,006 Combined statistical and rule-based part-of-speech tagging for text-to-speech synthesis 4 2010
8,719,014 Electronic device with text error correction based on voice recognition data 1 2010
9,318,108 Intelligent automated assistant 0 2011
8,781,836 Hearing assistance system for providing consistent human speech 0 2011
9,262,612 Device access using voice authentication 0 2011
8,812,294 Translating phrases from one language into another using an order-based set of declarative rules 0 2011
8,706,472 Method for disambiguating multiple readings in language conversion 6 2011
8,762,156 Speech recognition repair using contextual information 8 2011
8,688,446 Providing text input using speech data and non-speech data 15 2011
8,775,442 Semantic search using a single-source semantic model 11 2012
8,762,469 Electronic devices with voice command and contextual data processing capabilities 0 2012
8,713,119 Electronic devices with voice command and contextual data processing capabilities 0 2012
8,670,985 Devices and methods for identifying a prompt corresponding to a voice input in a sequence of prompts 0 2012
8,935,167 Exemplar-based latent perceptual modeling for automatic speech recognition 0 2012
9,117,447 Using event alert text as input to an automated assistant 1 2012
8,942,986 Determining user intent based on ontologies of domains 1 2012
8,903,716 Personalized vocabulary for digital assistant 0 2012
8,892,446 Service orchestration for intelligent automated assistant 4 2012
8,799,000 Disambiguation based on active input elicitation by intelligent automated assistant 1 2012
8,706,503 Intent deduction based on previous user interactions with voice assistant 12 2012
8,670,979 Active input elicitation by intelligent automated assistant 7 2012
8,660,849 Prioritizing selection criteria by automated assistant 11 2012
8,718,047 Text to speech conversion of text messages from mobile communication devices 0 2012
9,311,043 Adaptive audio feedback system and method 0 2013
8,751,238 Systems and methods for determining the language to use for speech generated by a text to speech engine 1 2013
8,930,191 Paraphrasing of user requests and results by automated digital assistant 1 2013
8,731,942 Maintaining context information between user interactions with a voice assistant 3 2013
9,280,610 Crowd sourcing information to fulfill user requests 0 2013
9,075,783 Electronic device with text error correction based on voice recognition data 0 2013
9,361,886 Providing text input using speech data and non-speech data 0 2013
9,389,729 Automated response to and sensing of user activity in portable devices 0 2013
9,190,062 User profiling for voice input processing 0 2014
9,368,114 Context-sensitive handling of interruptions 0 2014
9,300,784 System and method for emergency calls initiated by voice command 0 2014
9,338,493 Intelligent automated assistant for TV user interactions 0 2014
 
INTERACTIONS LLC (2)
* 7,149,687 Method of active learning for automatic speech recognition 27 2002
8,990,084 Method of active learning for automatic speech recognition 0 2014
 
RESOLVITY, INC. (1)
* 8,682,660 Method and system for post-processing speech recognition results 0 2009
 
MICROSOFT TECHNOLOGY LICENSING, LLC (3)
* 7,844,449 Scalable probabilistic latent semantic analysis 1 2006
* 2007/0239,431 Scalable probabilistic latent semantic analysis 1 2006
* 2009/0326,924 Projecting Semantic Information from a Language Independent Syntactic Model 2 2008
 
XYLON LLC (3)
6,904,405 Message recognition using shared language model 37 2002
* 8,204,737 Message recognition using shared language model 4 2005
* 2005/0171,783 Message recognition using shared language model 19 2005
 
GOOGLE INC. (1)
* 9,324,323 Speech recognition using topic-specific language models 0 2012
 
THE TRUSTEES OF THE STEVENS INSTITUTE OF TECHNOLOGY (1)
* 2012/0254,333 AUTOMATED DETECTION OF DECEPTION IN SHORT AND MULTILINGUAL ELECTRONIC MESSAGES 42 2012
 
RAYTHEON BBN TECHNOLOGIES CORP. (8)
7,401,023 Systems and methods for providing automated directory assistance using transcripts 14 2000
7,447,636 System and methods for using transcripts to train an automated directory assistance service 13 2005
7,890,539 Semantic matching using predicate-argument structure 11 2007
* 2009/0100,053 Semantic matching using predicate-argument structure 4 2007
8,131,536 Extraction-empowered machine translation 3 2007
* 2008/0215,309 Extraction-Empowered machine translation 8 2007
8,595,222 Methods and systems for representing, using and displaying time-varying information on the semantic web 3 2008
8,260,817 Semantic matching using predicate-argument structure 4 2011
 
UBS AG, STAMFORD BRANCH (1)
* 7,236,931 Systems and methods for automatic acoustic speaker adaptation in computer-assisted transcription systems 31 2003
 
INTERNATIONAL BUSINESS MACHINES CORPORATION (6)
* 6,577,999 Method and apparatus for intelligently managing multiple pronunciations for a speech recognition vocabulary 8 1999
* 6,385,579 Methods and apparatus for forming compound words for use in a continuous speech recognition system 25 1999
* 6,529,902 Method and system for off-line detection of textual topical changes and topic identification via likelihood based methods for improved language modeling 47 1999
* 7,644,057 System and method for electronic communication management 10 2004
* 7,752,159 System and method for classifying text 14 2007
* 2007/0294,199 SYSTEM AND METHOD FOR CLASSIFYING TEXT 15 2007
 
KONINKLIJKE PHILIPS ELECTRONICS N.V. (2)
* 7,424,428 Automatic dialog system with database language model 9 2002
* 2004/0034,518 Automatic dialog system with database language model 2 2002
 
SOPHIA SEARCH LIMITED (2)
* 7,747,593 Computer aided document retrieval 18 2004
* 2007/0174,267 Computer aided document retrieval 18 2004
 
BBN TECHNOLOGIES CORP. (1)
* 2004/0243,531 Methods and systems for representing, using and displaying time-varying information on the Semantic Web 20 2004
 
BELLSOUTH INTELLECTUAL PROPERTY CORPORATION (1)
6,751,595 Multi-stage large vocabulary speech recognition system and method 22 2001
 
ECOLLEGE.COM (2)
6,871,043 Variable types of sensory interaction for an on-line educational system 11 2002
6,965,752 On-line educational system having an electronic notebook feature 9 2003
 
SIEMENS AKTIENGESELLSCHAFT (1)
* 6,640,207 Method and configuration for forming classes for a language model based on linguistic classes 12 2001
 
MMODAL IP LLC (1)
8,959,102 Structured searching of dynamic structured document corpuses 1 2011
 
APTIMA, INC. (2)
9,165,254 Method and system to predict the likelihood of topics 0 2009
* 2010/0280,985 METHOD AND SYSTEM TO PREDICT THE LIKELIHOOD OF TOPICS 32 2009
 
SCANSOFT, INC. (1)
* 2004/0088,162 Systems and methods for automatic acoustic speaker adaptation in computer-assisted transcription systems 19 2003
 
AT&T INTELLECTUAL PROPERTY II, L.P. (20)
* 6,044,337 Selection of superwords based on criteria relevant to both speech recognition and understanding 82 1997
* 6,021,384 Automatic generation of superwords 116 1997
7,085,720 Method for task classification using morphemes 20 2000
7,158,935 Method and system for predicting problematic situations in a automated dialog 25 2000
* 6,751,584 Automatic clustering of tokens from a corpus for grammar acquisition 10 2001
8,392,188 Method and system for building a phonotactic model for domain independent speech recognition 2 2001
7,286,984 Method and system for automatically detecting morphemes in a task classification system using lattices 14 2002
7,356,462 Automatic clustering of tokens from a corpus for grammar acquisition 0 2003
7,139,698 System and method for generating morphemes 4 2003
8,433,558 Methods and systems for natural language understanding using human knowledge and collected data 1 2005
7,440,897 Method and system for automatically detecting morphemes in a task classification system using lattices 7 2006
7,957,970 Method and system for predicting problematic situations in automated dialog 3 2006
7,620,548 Method and system for automatic detecting morphemes in a task classification system using lattices 5 2007
7,966,174 Automatic clustering of tokens from a corpus for grammar acquisition 0 2008
8,010,361 Method and system for automatically detecting morphemes in a task classification system using lattices 5 2008
* 2008/0288,244 METHOD AND SYSTEM FOR AUTOMATICALLY DETECTING MORPHEMES IN A TASK CLASSIFICATION SYSTEM USING LATTICES 1 2008
8,200,491 Method and system for automatically detecting morphemes in a task classification system using lattices 3 2011
8,612,212 Method and system for automatically detecting morphemes in a task classification system using lattices 1 2013
8,798,990 Methods and systems for natural language understanding using human knowledge and collected data 0 2013
8,909,529 Method and system for automatically detecting morphemes in a task classification system using lattices 0 2013
 
INTEL CORPORATION (4)
* 7,346,495 Method and system for building a domain specific statistical language model from rule based grammar specifications 6 2000
* 7,275,033 Method and system for using rule-based knowledge to build a class-based domain specific statistical language model 12 2000
* 9,323,854 Method, apparatus and system for location assisted translation 0 2008
* 2010/0161,311 Method, apparatus and system for location assisted translation 8 2008
 
NIPPON TELEGRAPH AND TELEPHONE CORPORATION (3)
* 6,173,261 Grammar fragment acquisition using syntactic and semantic clustering 184 1998
* 8,666,744 Grammar fragment acquisition using syntactic and semantic clustering 1 2000
9,330,660 Grammar fragment acquisition using syntactic and semantic clustering 0 2014
 
AT&T ALEX HOLDINGS, LLC (8)
6,941,266 Method and system for predicting problematic dialog situations in a task classification system 64 2000
7,003,459 Method and system for predicting understanding errors in automated dialog systems 26 2001
6,751,591 Method and system for predicting understanding errors in a task classification system 85 2001
7,127,395 Method and system for predicting understanding errors in a task classification system 30 2004
7,529,667 Automated dialog system and method 6 2005
7,472,060 Automated dialog system and method 45 2005
7,440,893 Automated dialog method with first and second thresholds for adapted dialog strategy 7 2005
7,487,088 Method and system for predicting understanding errors in a task classification system 44 2006
 
PANASONIC INTELLECTUAL PROPERTY CORPORATION OF AMERICA (2)
* 6,182,039 Method and apparatus using probabilistic language model based on confusable sets for speech recognition 74 1998
* 6,233,561 Method for goal-oriented speech translation in hand-held devices using meaning extraction and dialogue 75 1999
 
AT&T CORP. (4)
* 6,317,707 Automatic clustering of tokens from a corpus for grammar acquisition 77 1998
* 6,415,248 Method for building linguistic models from a corpus 19 1999
* 2003/0191,625 Method and system for creating a named entity language model 75 2003
* 2008/0177,544 METHOD AND SYSTEM FOR AUTOMATIC DETECTING MORPHEMES IN A TASK CLASSIFICATION SYSTEM USING LATTICES 1 2007
* Cited By Examiner