A Statistical Model for Word Discovery in Transcribed Speech

A statistical model for segmentation and word discovery in continuous speech is presented. An incremental unsupervised learning algorithm to infer word boundaries based on this model is described. Results are also presented of empirical tests showing that the algorithm is competitive with other models that have been used for similar tasks.

[1]  P. Jusczyk,et al.  Infants' memory for spoken words. , 1997, Science.

[2]  J. Pind.  The Discovery of Spoken Language, Peter W. Jusczyk (Ed.). MIT Press (1997), ISBN 0 262 10058 4 , 1997 .

[3]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[4]  P. Jusczyk,et al.  Phonotactic and Prosodic Effects on Word Segmentation in Infants , 1999, Cognitive Psychology.

[5]  Morten H. Christiansen,et al.  Learning to Segment Speech Using Multiple Cues: A Connectionist Model , 1998 .

[6]  T. Poggio,et al.  MASSACHUSETTS INSTITUTE OF TECHNOLOGY ARTIFICIAL INTELLIGENCE LABORATORY and CENTER FOR BIOLOGICAL AND COMPUTATIONAL LEARNING DEPARTMENT OF BRAIN AND COGNITIVE SCIENCES , 2001 .

[7]  David Haussler,et al.  Quantifying Inductive Bias: AI Learning Algorithms and Valiant's Learning Framework , 1988, Artif. Intell..

[8]  Ian H. Witten,et al.  The zero-frequency problem: Estimating the probabilities of novel events in adaptive text compression , 1991, IEEE Trans. Inf. Theory.

[9]  Gwyneth Tseng,et al.  Chinese text segmentation for text retrieval: achievements and problems , 1993 .

[10]  T. A. Cartwright,et al.  Distributional regularity and phonotactic constraints are useful for segmentation , 1996, Cognition.

[11]  E. Newport,et al.  WORD SEGMENTATION : THE ROLE OF DISTRIBUTIONAL CUES , 1996 .

[12]  C Snow,et al.  Child language data exchange system , 1984, Journal of Child Language.

[13]  Eleanor Olds Batchelder,et al.  Computational evidence for the use of frequency information in discovery of the infant's first lexicon , 1997 .

[14]  Van Nostrand,et al.  Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm , 1967 .

[15]  Lillian Lee,et al.  Unsupervised Statistical Segmentation of Japanese Kanji Strings , 1999 .

[16]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[17]  WuZimin,et al.  Chinese text segmentation for text retrieval , 1993 .

[18]  Carl de Marcken,et al.  The Unsupervised Acquisition of a Lexicon from Continuous Speech , 1995, ArXiv.

[19]  Frederick Jelinek,et al.  Statistical methods for speech recognition , 1997 .

[20]  P. Jusczyk,et al.  Infants' preference for the predominant stress patterns of English words. , 1993, Child development.

[21]  Slava M. Katz,et al.  Estimation of probabilities from sparse data for the language model component of a speech recognizer , 1987, IEEE Trans. Acoust. Speech Signal Process..

[22]  Anne Cutler,et al.  The predominance of strong initial syllables in the English vocabulary , 1987 .