Using Natural-Language Knowledge Sources in Speech Recognition

High accuracy speech recognition requires a language model, to specify what word sequences are possible or at least likely. Standard n-gram language models for speech recognition ignore linguistic structures, but more linguistically sophisticated language models are possible. Unification grammars are widely used in natural languageand these can be compiled into non-left-recursive context-free grammars that can then be used in realtime speech recognizers by dynamically expanding them into state-transition networks. A hybrid language model incorporating both a unification grammar and n-gram statistics has been shown to increase speech recognition accuracy. Probabilistic context-free grammars and probabilistic unification grammars are also possible.

[1]  Adam Cheyer,et al.  CommandTalk: A Spoken-Language Interface for Battlefield Simulations , 1997, ANLP.

[2]  Michael Collins,et al.  A New Statistical Parser Based on Bigram Lexical Dependencies , 1996, ACL.

[3]  Douglas E. Appelt,et al.  Combining Linguistic and Statistical Knowledge Sources in Natural-Language Processing for ATIS , 1995 .

[4]  Ralph Grishman,et al.  Smoothing of Automatically Generated Selectional Constraints , 1993, HLT.

[5]  R. J. Nelson,et al.  Introduction to Automata , 1968 .

[6]  Yen-Lu Chow Salim RoJor.  SPEECH UNDERSTANDING USING A UNIFICATION GRAMMAR , 1989 .

[7]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .

[8]  Salim Roukos.  Integrating Speech and Natural Language , 1989, HLT.

[9]  John D. Lafferty,et al.  Towards History-based Grammars: Using Richer Models for Probabilistic Parsing , 1993, ACL.

[10]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[11]  Douglas E. Appelt,et al.  GEMINI: A Natural Language System for Spoken-Language Understanding , 1993, ACL.

[12]  Mehryar Mohri,et al.  Finite-State Transducers in Language and Speech Processing , 1997, CL.

[13]  Robert C. Moore.  Logic and Representation , 1994 .

[14]  Joshua Goodman,et al.  Probabilistic Feature Grammars , 1997, IWPT.

[15]  Richard M. Schwartz,et al.  Efficient, High-Performance Algorithms for N-Best Search , 1990, HLT.

[16]  David M. Magerman.  Statistical Decision-Tree Models for Parsing , 1995, ACL.

[17]  William A. Woods,et al.  Computational Linguistics Transition Network Grammars for Natural Language Analysis , 2022 .

[18]  C. Pollard,et al.  Center for the Study of Language and Information , 2022 .

[19]  Ted Briscoe,et al.  Generalized Probabilistic LR Parsing of Natural Language (Corpora) with Unification-Based Grammars , 1993, CL.

[20]  Geoffrey K. Pullum,et al.  Natural languages and context-free languages , 1982 .

[21]  P MarcusMitchell,et al.  Building a large annotated corpus of English , 1993 .

[22]  David Stallard,et al.  The BBN Spoken Language System , 1989, HLT.

[23]  Christopher Culy,et al.  The complexity of the vocabulary of Bambara , 1985 .

[24]  Hy Murveit,et al.  Integrating natural language constraints into HMM-based speech recognition , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[25]  François Andry,et al.  Interleaving Syntax and Semantics in an Effecient Bottom-Up Parser , 1994, ACL.

[26]  Stuart M. Shieber,et al.  Evidence against the context-freeness of natural language , 1985 .

[27]  守屋 悦朗,et al.  J.E.Hopcroft, J.D. Ullman 著, "Introduction to Automata Theory, Languages, and Computation", Addison-Wesley, A5変形版, X+418, \6,670, 1979 , 1980 .

[28]  H. Alshawi,et al.  The Core Language Engine , 1994 .

[29]  Michael Collins,et al.  Three Generative, Lexicalised Models for Statistical Parsing , 1997, ACL.

[30]  Mei-Yuh Hwang,et al.  Microsoft Windows highly intelligent speech recognizer: Whisper , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[31]  John Lafferty,et al.  Grammatical Trigrams: A Probabilistic Model of Link Grammar , 1992 .

[32]  Richard M. Schwartz,et al.  The N-Best Algorithm: Efficient Procedure for Finding Top N Sentence Hypotheses , 1989, HLT.

[33]  Eugene Charniak,et al.  Parsing with Context-Free Grammars and Word Statistics , 1995 .

[34]  Hy Murveit,et al.  Integrating Speech and Natural-Language Processing , 1989, HLT.

[35]  Pierre Dupont,et al.  Dynamic use of syntactical knowledge in continuous speech recognition , 1993, EUROSPEECH.