The Resource Statistical optimization of acoustic models for large vocabulary speech recognition, by Rusheng Hu, (electronic resource)

Statistical optimization of acoustic models for large vocabulary speech recognition, by Rusheng Hu, (electronic resource)

Label
Statistical optimization of acoustic models for large vocabulary speech recognition
Title
Statistical optimization of acoustic models for large vocabulary speech recognition
Statement of responsibility
by Rusheng Hu
Creator
Contributor
Thesis advisor
Subject
Genre
Language
eng
Summary
This dissertation investigates optimization of acoustic models in speech recognition. Two new optimization methods are proposed for phonetic decision tree (PDT) search and Hidden Markov modeling (HMM)-- the knowledge-based adaptive PDT algorithm and the HMM gradient boosting algorithm. Investigations are conducted to applying both methods to improve word error rate of the state-of-the-art speech recognition system. However, these two methods are developed in a general machine learning background and their applications are not limited to speech recognition. The HMM gradient boosting method is based on a function approximation scheme from the perspective of optimization in function space rather than the parameter space, based on the fact that the Gaussian mixture model in each HMM state is an additive model of homogeneous functions (Gaussians). It provides a new scheme which can jointly optimize model structure and parameters. Experiments are conducted on the World Street Journal (WSJ) task and good improvements on word error rate are observed. The knowledge-based adaptive PDT algorithm is developed under a trend toward knowledge-based systems and aims at optimizing the mapping from contextual phones to articulatory states by maximizing implicit usage of the phonological and phonetic information, which is presumed to be contained in large data corpus. A computational efficient algorithm is developed to incorporate this prior knowledge in PDT construction. This algorithm is evaluated on the Telehealth conversational speech recognition and significant improvement on system performance is achieved
Cataloging source
MUU
http://library.link/vocab/creatorDate
1971-
http://library.link/vocab/creatorName
Hu, Rusheng
Dissertation year
2006.
Granting institution
Thesis (Ph. D.) University of Missouri-Columbia
Illustrations
illustrations
Index
no index present
Literary form
non fiction
Nature of contents
  • dictionaries
  • bibliography
  • theses
http://library.link/vocab/relatedWorkOrContributorName
Zhao, Yunxin
http://library.link/vocab/subjectName
  • Speech perception
  • Pattern recognition systems
  • Hidden Markov models
Target audience
specialized
Label
Statistical optimization of acoustic models for large vocabulary speech recognition, by Rusheng Hu, (electronic resource)
Instantiates
Publication
Note
  • The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general description, or public abstract, appears in the public.pdf file
  • Title from title screen of research.pdf file (viewed on August 2, 2007)
  • Vita
Bibliography note
Includes bibliographical references
Carrier category
online resource
Carrier category code
  • cr
Carrier MARC source
rdacarrier
Color
mixed
Content category
text
Content type code
  • txt
Content type MARC source
rdacontent
Control code
162129635
Dimensions
unknown
Form of item
electronic
Media category
computer
Media MARC source
rdamedia
Media type code
  • c
Specific material designation
remote
System control number
(OCoLC)162129635
System details
Mode of access: World Wide Web
Label
Statistical optimization of acoustic models for large vocabulary speech recognition, by Rusheng Hu, (electronic resource)
Publication
Note
  • The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general description, or public abstract, appears in the public.pdf file
  • Title from title screen of research.pdf file (viewed on August 2, 2007)
  • Vita
Bibliography note
Includes bibliographical references
Carrier category
online resource
Carrier category code
  • cr
Carrier MARC source
rdacarrier
Color
mixed
Content category
text
Content type code
  • txt
Content type MARC source
rdacontent
Control code
162129635
Dimensions
unknown
Form of item
electronic
Media category
computer
Media MARC source
rdamedia
Media type code
  • c
Specific material designation
remote
System control number
(OCoLC)162129635
System details
Mode of access: World Wide Web

Library Locations

  • Health Sciences LibraryBorrow it
    2411 Holmes St, Kansas City, Kansas City, MO, 64108, US
    39.083418 -94.575323
  • LaBudde Special CollectionsBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.034642 -94.576835
  • Leon E. Bloch Law LibraryBorrow it
    500 E. 52nd Street, Kansas City, MO, 64110, US
    39.032488 -94.581967
  • Marr Sound ArchivesBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.034642 -94.576835
  • Miller Nichols LibraryBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.035061 -94.576518
  • UMKCBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.035061 -94.576518
  • UMKCBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
Processing Feedback ...