Document Detail

An overlapping-feature-based phonological model incorporating linguistic constraints: applications to speech recognition.
MedLine Citation:
PMID:  11863165     Owner:  NLM     Status:  MEDLINE    
Modeling phonological units of speech is a critical issue in speech recognition. In this paper, our recent development of an overlapping-feature-based phonological model that represents long-span contextual dependency in speech acoustics is reported. In this model, high-level linguistic constraints are incorporated in automatic construction of the patterns of feature-overlapping and of the hidden Markov model (HMM) states induced by such patterns. The main linguistic information explored includes word and phrase boundaries, morpheme, syllable, syllable constituent categories, and word stress. A consistent computational framework developed for the construction of the feature-based model and the major components of the model are described. Experimental results on the use of the overlapping-feature model in an HMM-based system for speech recognition show improvements over the conventional triphone-based phonological model.
Jiping Sun; Li Deng
Related Documents :
18003405 - Automatic classification of subjects with and without sleep apnea through snoring analy...
1482915 - Probability estimation for biomedical classification problems.
9644575 - An algorithm for the automatic differentiation between the speech of normals and patien...
19366645 - Rough neuro-fuzzy structures for classification with missing data.
24833995 - The domestic livestock resources of turkey: status, use and some physical characteristi...
21729295 - Comparative analysis of methods for detecting interacting loci.
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  The Journal of the Acoustical Society of America     Volume:  111     ISSN:  0001-4966     ISO Abbreviation:  J. Acoust. Soc. Am.     Publication Date:  2002 Feb 
Date Detail:
Created Date:  2002-02-26     Completed Date:  2002-03-29     Revised Date:  2006-12-27    
Medline Journal Info:
Nlm Unique ID:  7503051     Medline TA:  J Acoust Soc Am     Country:  United States    
Other Details:
Languages:  eng     Pagination:  1086-101     Citation Subset:  IM    
University of Waterloo, Ontario, Canada.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Sound Spectrography
Speech Perception / physiology*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  On application of adaptive decorrelation filtering to assistive listening.
Next Document:  Ultrasound-induced lung hemorrhage: role of acoustic boundary conditions at the pleural surface.