Coverart for item
The Resource Speech recognition algorithms using weighted finite-state transducers, Takaaki Hori, Atsushi Nakamura

Speech recognition algorithms using weighted finite-state transducers, Takaaki Hori, Atsushi Nakamura

Label
Speech recognition algorithms using weighted finite-state transducers
Title
Speech recognition algorithms using weighted finite-state transducers
Statement of responsibility
Takaaki Hori, Atsushi Nakamura
Creator
Contributor
Subject
Language
eng
Summary
This book introduces the theory, algorithms, and implementation techniques for efficient decoding in speech recognition mainly focusing on the Weighted Finite-State Transducer (WFST) approach. The decoding process for speech recognition is viewed as a search problem whose goal is to find a sequence of words that best matches an input speech signal. Since this process becomes computationally more expensive as the system vocabulary size increases, research has long been devoted to reducing the computational cost. Recently, the WFST approach has become an important state-of-the-art speech recognition technology, because it offers improved decoding speed with fewer recognition errors compared with conventional methods. However, it is not easy to understand all the algorithms used in this framework, and they are still in a black box for many people. In this book, we review the WFST approach and aim to provide comprehensive interpretations of WFST operations and decoding algorithms to help anyone who wants to understand, develop, and study WFST-based speech recognizers. We also mention recent advances in this framework and its applications to spoken language processing
Member of
Cataloging source
CIN
http://bibfra.me/vocab/lite/collectionName
Synthesis digital library of engineering and computer science
http://library.link/vocab/creatorName
Hori, Takaaki
Illustrations
illustrations
Index
no index present
LC call number
TK7895.S65
LC item number
H67 2013
Literary form
non fiction
Nature of contents
bibliography
http://library.link/vocab/relatedWorkOrContributorName
  • Nakamura, Atsushi, 1963
  • Morgan & Claypool Publishers
Series statement
Synthesis lectures on speech and audio processing
Series volume
#10
http://library.link/vocab/subjectName
  • Automatic speech recognition
  • Speech processing systems
Label
Speech recognition algorithms using weighted finite-state transducers, Takaaki Hori, Atsushi Nakamura
Instantiates
Publication
Note
"This volume is a printed version of a work that appears in the Synthesis digital library of engineering and computer science"--P. 4 of cover
Bibliography note
Includes bibliographical references
Carrier category
volume
Carrier category code
  • nc
Carrier MARC source
rdacarrier
Content category
text
Content type code
  • txt
Content type MARC source
rdacontent
Contents
1. Introduction -- 2. Brief overview of speech recognition -- 3. Introduction to weighted finite-state transducers -- 4. Speech recognition by weighted finite-state transducers -- 5. Dynamic decoders with on-the-fly WFST operations -- 6. Summary and perspective
Control code
858949754
Dimensions
24 cm
Extent
xii, 150 pages
Isbn
9781608454730
Media category
unmediated
Media MARC source
rdamedia
Media type code
  • n
Other physical details
illustrations
System control number
(OCoLC)858949754
Label
Speech recognition algorithms using weighted finite-state transducers, Takaaki Hori, Atsushi Nakamura
Publication
Note
"This volume is a printed version of a work that appears in the Synthesis digital library of engineering and computer science"--P. 4 of cover
Bibliography note
Includes bibliographical references
Carrier category
volume
Carrier category code
  • nc
Carrier MARC source
rdacarrier
Content category
text
Content type code
  • txt
Content type MARC source
rdacontent
Contents
1. Introduction -- 2. Brief overview of speech recognition -- 3. Introduction to weighted finite-state transducers -- 4. Speech recognition by weighted finite-state transducers -- 5. Dynamic decoders with on-the-fly WFST operations -- 6. Summary and perspective
Control code
858949754
Dimensions
24 cm
Extent
xii, 150 pages
Isbn
9781608454730
Media category
unmediated
Media MARC source
rdamedia
Media type code
  • n
Other physical details
illustrations
System control number
(OCoLC)858949754

Library Locations

    • Engineering Library & Technology CommonsBorrow it
      W2001 Lafferre Hall, Columbia, MO, 65211, US
      38.946102 -92.330125
Processing Feedback ...