Accession Number : ADA262968


Title :   Segment-Based Acoustic Models for Continuous Speech Recognition


Descriptive Note : Progress rept. Jan-Mar 1993,


Corporate Author : BOSTON UNIV MA


Personal Author(s) : Ostendorf, Mari ; Rohlicek, J R


Full Text : http://www.dtic.mil/dtic/tr/fulltext/u2/a262968.pdf


Report Date : 05 Apr 1993


Pagination or Media Count : 26


Abstract : This research aims to develop new and more accurate acoustic models for speaker-independent continuous speech recognition, by extending previous work in segment-based modeling and by introducing a new hierarchical approach to representing intra-utterance statistical dependencies. These techniques, which are more costly than traditional approaches because of the large search space associated with higher order models, are made feasible through rescoring a set of HMM-generated N-best sentence hypotheses. We expect these different acoustic modeling methods 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.


Descriptors :   *MATHEMATICAL MODELS , *SPEECH RECOGNITION , ALGORITHMS , VOCABULARY , SEGMENTED , WORD RECOGNITION , CONTINUITY , STOCHASTIC PROCESSES , STATISTICS


Subject Categories : Voice Communications


Distribution Statement : APPROVED FOR PUBLIC RELEASE