Accession Number : ADA289969
Title : Segment-Based Acoustic Models for Continuous Speech Recognition.
Descriptive Note : Progress rept. 1 Jul-31 Dec 94,
Corporate Author : BOSTON UNIV MA
Personal Author(s) : Ostendorf, Mari ; Rohlicek, J. R.
PDF Url : ADA289969
Report Date : 31 DEC 1994
Pagination or Media Count : 18
Abstract : This research aims to develop new and more accurate stochastic models for speaker-independent continuous speech recognition by extending previous work in segment-based modeling, by introducing a new hierarchical approach to representing intra-utterance statistical dependencies, and by developing language models that capture topic dependencies. These techniques, which have high computational costs because of the large search space associated with higher order models, are made feasible through a multi-pass search strategy that involves rescoring a constrained space given by an HMM decoding. We expect these different modeling techniques to result in improved recognition performance over that achieved by current systems, which handle only frame-based observations and assume that these observations are independent given an underlying state sequence. The primary research efforts and results over the last two quarters have included implementation of several software system improvements to enable research in more general distribution clustering and score combination weight estimation; development of a constrained EM algorithm for training the mixture language model which led to a small improvement in performance over Viterbi-style training; development of a mixture version of cache language modeling, together with a new content- word cache model, obtaining a small error reduction for short (3-sentence articles); implementation and evaluation of three lattice search algorithms, providing an understanding of conditions under which the different algorithms are most appropriate. (AN)
Descriptors : *SPEECH RECOGNITION, *PATTERN RECOGNITION, COMPUTER PROGRAMS, MATHEMATICAL MODELS, ALGORITHMS, SOFTWARE ENGINEERING, COMPUTATIONS, STOCHASTIC PROCESSES, ACCURACY, ESTIMATES, CLUSTERING, KNOWLEDGE BASED SYSTEMS, VOCABULARY, DYNAMIC PROGRAMMING, HIERARCHIES, ERROR CORRECTION CODES, SOUND PITCH, NATURAL LANGUAGE, WORD RECOGNITION, AUDITORY SIGNALS, SPEECH REPRESENTATION, DECODING, PHONETICS.
Subject Categories : Linguistics
Distribution Statement : APPROVED FOR PUBLIC RELEASE