US Patent No: 6,173,261

Number of patents in Portfolio can not be more than 2000

Grammar fragment acquisition using syntactic and semantic clustering

Stats

ATTORNEY / AGENT: (SPONSORED)
 

Importance

Loading Importance Indicators... loading....

Abstract

A method and apparatus are provided for automatically acquiring grammar fragments for recognizing and understanding fluently spoken language. Grammar fragments representing a set of syntactically and semantically similar phrases may be generated using three probability distributions: of succeeding words, of preceding words, and of associated call-types. The similarity between phrases may be measured by applying Kullback-Leibler distance to these three probability distributions. Phrases being close in all three distances may be clustered into a grammar fragment.

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

First Claim

Related Publications

Loading Related Publications... loading....

Patent Owner(s)

Patent OwnerAddressTotal Patents
AT&T CORP.NEW YORK, NY4134
NIPPON TELEGRAPH AND TELEPHONE CORPORATIONTOKYO2402

International Classification(s)

  • [Classification Symbol]
  • [Patents Count]

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
Arai, Kazuhiro Kadoma, JP 60 323
Gorin, Allen Louis Berkeley Heights, NJ 63 1169
Riccardi, Giuseppe Hoboken, NJ 59 604
Wright, Jeremy Huntley Berkley Heights, NJ 28 420

Cited Art

Patent Info (Count) # Cites Year
 
AT&T CORP. (2)
5,675,707 Automated call router system and method 113 1995
5,860,063 Automated meaningful phrase clustering 83 1997
 
APPLE INC. (1)
5,839,106 Large-vocabulary speech recognition using an integrated syntactic and semantic statistical language model 88 1996
 
DRAGON SYSTEMS, INC. (1)
4,903,305 Method for representing word models for use in speech recognition 99 1989
 
INTERNATIONAL BUSINESS MACHINES CORPORATION (1)
6,023,673 Hierarchical labeler in a speech recognition system 30 1997
 
KABUSHIKI KAISHA TOSHIBA (1)
5,457,768 Speech recognition apparatus using syntactic and semantic analysis 65 1992
 
LUCENT TECHNOLOGIES INC. (1)
5,794,193 Automated phrase generation 60 1995
 
MATSUSHITA ELECTRIC INDUSTRIAL CO., LTD. (1)
5,099,425 Method and apparatus for analyzing the semantics and syntax of a sentence or a phrase 66 1989

Patent Citation Ranking

Forward Cites

Patent Info (Count) # Cites Year
 
PHOENIX SOLUTIONS, INC. (21)
7,392,185 Speech based learning/training system using semantic decoding 33 2003
7,725,307 Query engine for processing voice based queries including semantic decoding 25 2003
7,555,431 Method for processing speech using dynamic grammars 26 2004
7,376,556 Method for processing speech signal features for streaming transport 24 2004
7,729,904 Partial speech processing device and method for use in distributed systems 19 2004
7,702,508 System and method for natural language processing of query answers 20 2004
7,657,424 System and method for processing sentence based queries 20 2004
7,624,007 System and method for natural language processing of sentence based queries 24 2004
7,277,854 Speech recognition system interactive agent 48 2005
7,225,125 Speech recognition system trained with regional speech characteristics 24 2005
7,139,714 Adjustable resource based speech recognition system 26 2005
7,831,426 Network based interactive speech recognition system 20 2006
7,647,225 Adjustable resource based speech recognition system 17 2006
8,352,277 Method of interacting through speech with a web-connected server 0 2007
7,725,320 Internet based speech recognition system with dynamic grammars 16 2007
7,698,131 Speech recognition system for client devices having differing computing capabilities 14 2007
7,912,702 Statistical language model trained with semantic variants 14 2007
7,873,519 Natural language speech lattice containing semantic variants 22 2007
7,672,841 Method for processing speech data for a distributed recognition system 16 2008
8,229,734 Semantic decoding of user queries 0 2008
7,725,321 Speech based query system using semantic decoding 17 2008
 
AT&T CORP. (13)
6,415,248 Method for building linguistic models from a corpus 14 1999
7,085,720 Method for task classification using morphemes 15 2000
7,158,935 Method and system for predicting problematic situations in a automated dialog 21 2000
6,941,266 Method and system for predicting problematic dialog situations in a task classification system 45 2000
7,003,459 Method and system for predicting understanding errors in automated dialog systems 23 2001
6,751,591 Method and system for predicting understanding errors in a task classification system 49 2001
7,286,984 Method and system for automatically detecting morphemes in a task classification system using lattices 9 2002
7,263,486 Active learning for spoken language understanding 6 2003
7,139,698 System and method for generating morphemes 3 2003
7,127,395 Method and system for predicting understanding errors in a task classification system 21 2004
7,472,060 Automated dialog system and method 23 2005
7,440,893 Automated dialog method with first and second thresholds for adapted dialog strategy 7 2005
7,440,897 Method and system for automatically detecting morphemes in a task classification system using lattices 5 2006
 
AT&T INTELLECTUAL PROPERTY II, L.P. (11)
8,392,188 Method and system for building a phonotactic model for domain independent speech recognition 0 2001
7,933,774 System and method for automatic generation of a natural language understanding model 0 2004
8,185,399 System and method of providing an automated data-collection in spoken dialog systems 1 2005
7,529,667 Automated dialog system and method 6 2005
7,487,088 Method and system for predicting understanding errors in a task classification system 25 2006
7,957,970 Method and system for predicting problematic situations in automated dialog 1 2006
7,742,918 Active learning for spoken language understanding 0 2007
7,620,548 Method and system for automatic detecting morphemes in a task classification system using lattices 3 2007
8,010,361 Method and system for automatically detecting morphemes in a task classification system using lattices 3 2008
7,933,773 Natural language understanding monitoring system for identifying a task 1 2009
8,200,491 Method and system for automatically detecting morphemes in a task classification system using lattices 0 2011
 
NOVELL INTELLECTUAL PROPERTY HOLDINGS, INC. (8)
7,152,031 Construction, manipulation, and comparison of a multi-dimensional semantic space 21 2000
7,197,451 Method and mechanism for the creation, maintenance, and comparison of semantic abstracts 23 2000
7,286,977 Intentional-stance characterization of a general content stream or repository 9 2000
7,389,225 Method and mechanism for superpositioning state vectors in a semantic abstract 8 2000
7,562,011 Intentional-stance characterization of a general content stream or repository 8 2006
7,653,530 Method and mechanism for the creation, maintenance, and comparison of semantic abstracts 0 2006
7,672,952 System and method of semantic correlation of rich content 0 2006
8,131,741 Construction, manipulation, and comparison of a multi-dimensional semantic space 0 2007
 
MICROSOFT CORPORATION (6)
7,080,004 Grammar authoring system 10 2001
7,031,918 Generating a task-adapted acoustic model from one or more supervised and/or unsupervised corpora 10 2002
7,006,972 Generating a task-adapted acoustic model from one or more different corpora 4 2002
7,263,487 Generating a task-adapted acoustic model from one or more different corpora 1 2005
8,249,871 Word clustering for input data 1 2005
8,244,521 Paraphrasing the web by search-based data collection 0 2007
 
ELIZA CORPORATION (5)
7,366,766 Web-based speech recognition with scripting and semantic objects 4 2001
7,120,585 Remote server object architecture for speech recognition 7 2001
6,868,380 Speech recognition system and method for generating phonotic estimates 18 2001
7,370,086 Web-based speech recognition with scripting and semantic objects 4 2002
8,024,422 Web-based speech recognition with scripting and semantic objects 0 2008
 
GOOGLE INC. (5)
6,510,411 Task oriented dialog model and manager 99 1999
7,657,423 Automatic completion of fragments of text 7 2003
8,219,385 Computer-implemented method and system for conducting a search of electronically stored information 0 2008
8,024,178 Automatic completion of fragments of text 0 2009
8,280,722 Automatic completion of fragments of text 0 2011
 
NUANCE COMMUNICATIONS, INC. (5)
7,072,837 Method for processing initially recognized speech in a speech recognition session 2 2001
7,143,035 Methods and apparatus for generating dialog state conditioned language models 5 2002
8,032,358 Classifying text via topical analysis, for applications to speech recognition 0 2003
8,086,463 Dynamically generating a vocal help prompt in a multimodal application 13 2006
7,853,449 Methods and apparatus for generating dialog state conditioned language models 0 2008
 
TELSTRA CORPORATION LIMITED (4)
7,712,031 System and process for developing a voice application 4 2003
8,046,227 Development system for a dialog system 4 2003
7,917,363 System for predicting speech recognition accuracy and development for a dialog system 0 2004
8,296,129 System and process for grammatical inference 0 2004
 
NOVELL, INC. (3)
8,386,475 Attribution analysis and correlation 0 2008
8,301,622 Identity analysis and correlation 1 2008
8,296,297 Content analysis and correlation 1 2008
 
FLUENTIAL, LLC (2)
8,374,871 Methods for creating a phrase thesaurus 0 2002
8,442,812 Phrase-based dialogue modeling with particular application to creating a recognition grammar for a voice-controlled user interface 0 2004
 
MULTIMODAL TECHNOLOGIES, LLC (2)
8,335,688 Document transcription system training 0 2004
8,412,521 Discriminative training of document transcription system 0 2005
 
XEROX CORPORATION (2)
8,374,844 Hybrid system for named entity resolution 0 2007
8,370,128 Semantically-driven extraction of relations between named entities 0 2008
 
APPLE INC. (1)
7,149,695 Method and apparatus for speech recognition using semantic inference and word agglomeration 9 2000
 
AVAYA INC. (1)
7,054,435 Apparatus and method for determining a minimal time bound for performing tone detection 0 2002
 
BRITISH TELECOMMUNICATIONS PUBLIC LIMITED COMPANY (1)
6,839,671 Learning of dialogue states and language model of spoken information system 25 2002
 
FRANCE TELECOM (1)
6,973,168 Method of identifying a caller with a telephone service operator 1 2001
 
INTEL CORPORATION (1)
7,257,529 Apparatus and method for an automated grammar file expansion tool 3 2001
 
LYMBA CORPORATION (1)
8,380,511 System and method for semantic categorization 0 2007
 
ORACLE INTERNATIONAL CORPORATION (1)
7,177,922 Policy enforcement using the semantic characterization of traffic 5 2000
 
PARITY COMMUNICATIONS, INC. (1)
7,366,759 Method and system for characterizing relationships in social networks 33 2002
 
SAP AG (1)
8,156,142 Semantically weighted searching in a governed corpus of terms 0 2008
 
SBC TECHNOLOGY RESOURCES, INC. (1)
7,224,790 Method to identify and categorize customer's goals and behaviors within a customer service center environment 2 2000
 
SIEMENS ENTERPRISE COMMUNICATIONS GMBH & CO. KG (1)
7,162,424 Method and system for defining a sequence of sound modules for synthesis of a speech signal in a tonal language 0 2002
 
Other [Check patent profile for assignment information] (2)
7,392,174 Natural-language processing system using a large corpus 2 2001
8,229,733 Method and apparatus for linguistic independent parsing in a natural language systems 1 2006