Central Library, Indian Institute of Technology Delhi
केंद्रीय पुस्तकालय, भारतीय प्रौद्योगिकी संस्थान दिल्ली

Discriminative learning for speech recognition (Record no. 237613)

MARC details
000 -LEADER
fixed length control field 05376nam a2200565 i 4500
001 - CONTROL NUMBER
control field 6812876
003 - CONTROL NUMBER IDENTIFIER
control field IEEE
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20220822104737.0
006 - FIXED-LENGTH DATA ELEMENTS--ADDITIONAL MATERIAL CHARACTERISTICS
fixed length control field m eo d
007 - PHYSICAL DESCRIPTION FIXED FIELD--GENERAL INFORMATION
fixed length control field cr cn |||m|||a
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 080925s2008 caua ob 000 0 eng d
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
International Standard Book Number 9781598293098 (ebook)
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
International Standard Book Number 9781598293081 (pbk.)
024 7# - OTHER STANDARD IDENTIFIER
Standard number or code 10.2200/S00134ED1V01Y200807SAP004
Source of number or code doi
035 ## - SYSTEM CONTROL NUMBER
System control number (CaBNVSL)gtp00531414
035 ## - SYSTEM CONTROL NUMBER
System control number (OCoLC)256798648
040 ## - CATALOGING SOURCE
Original cataloging agency WAU
Transcribing agency WAU
Modifying agency CaBNVSL
050 #4 - LIBRARY OF CONGRESS CALL NUMBER
Classification number TK7895.S65
Item number H43 2008
082 04 - DEWEY DECIMAL CLASSIFICATION NUMBER
Classification number 401/.9
Edition number 22
100 1# - MAIN ENTRY--PERSONAL NAME
Personal name He, Xiaodong,
Dates associated with a name 1973-
245 10 - TITLE STATEMENT
Title Discriminative learning for speech recognition
Medium [electronic resource] :
Remainder of title theory and practice /
Statement of responsibility, etc. Xiaodong He and Li Deng.
260 ## - PUBLICATION, DISTRIBUTION, ETC.
Place of publication, distribution, etc. San Rafael, Calif. (1537 Fourth Street, San Rafael, CA 94901 USA) :
Name of publisher, distributor, etc. Morgan & Claypool Publishers,
Date of publication, distribution, etc. c2008.
300 ## - PHYSICAL DESCRIPTION
Extent 1 electronic text (vii, 112 p. : ill.) :
Other physical details digital file.
490 1# - SERIES STATEMENT
Series statement Synthesis lectures on speech and audio processing,
International Standard Serial Number 1932-1678 ;
Volume/sequential designation #4
538 ## - SYSTEM DETAILS NOTE
System details note Mode of access: World Wide Web.
538 ## - SYSTEM DETAILS NOTE
System details note System requirements: Adobe Acrobat Reader.
500 ## - GENERAL NOTE
General note Part of: Synthesis digital library of engineering and computer science.
500 ## - GENERAL NOTE
General note Series from website.
504 ## - BIBLIOGRAPHY, ETC. NOTE
Bibliography, etc. note Includes bibliographical references (p. 107-110).
505 0# - FORMATTED CONTENTS NOTE
Formatted contents note Introduction and background -- What is discriminative learning? -- What is speech recognition? -- Roles of discriminative learning in speech recognition -- Background: basic probability distributions -- Background: basic optimization concepts and techniques -- Organization of the book -- Statistical speech recognition: a tutorial -- Language modeling -- Acoustic modeling and HMMs -- Discriminative learning: a unified objective function -- A unified discriminative training criterion -- MMI and its unified form -- MCE and its unified form -- Minimum phone/word error and its unified form -- Discussions and comparisons -- Discriminative learning algorithm for exponential-family distributions -- Exponential-family models for classification -- Construction of auxiliary functions -- GT learning for exponential-family distributions -- Estimation formulas for two exponential-family distributions -- Discriminative learning algorithm for hidden Markov model -- Estimation formulas for discrete HMM -- Estimation formulas for CDHMM -- Relationship with gradient-based methods -- Setting constant D for GT-based optimization -- Practical implementation of discriminative learning -- Computing Dg (i, r, t) in growth-transform formulas -- Computing Dg (i, r, t) using lattices -- Arbitrary exponent scaling in MCE implementation -- Arbitrary slope in defining MCE cost function -- Selected experimental results -- Experimental results on small ASR tasks TIDIGITS -- Telephony LV-ASR applications -- Epilogue -- Summary of book contents -- Summary of contributions -- Remaining theoretical issue and future direction.
506 1# - RESTRICTIONS ON ACCESS NOTE
Terms governing access Abstract freely available; full-text restricted to subscribers or individual document purchasers.
510 0# - CITATION/REFERENCES NOTE
Name of source Compendex
510 0# - CITATION/REFERENCES NOTE
Name of source INSPEC
510 0# - CITATION/REFERENCES NOTE
Name of source Google scholar
510 0# - CITATION/REFERENCES NOTE
Name of source Google book search
520 ## - SUMMARY, ETC.
Summary, etc. In this book, we introduce the background and mainstream methods of probabilistic modeling and discriminative parameter optimization for speech recognition. The specific models treated in depth include the widely used exponential-family distributions and the hidden Markov model. A detailed study is presented on unifying the common objective functions for discriminative learning in speech recognition, namely maximum mutual information (MMI), minimum classification error, and minimum phone/word error. The unification is presented, with rigorous mathematical analysis, in a common rational-function form. This common form enables the use of the growth transformation (or extended Baum-Welch) optimization framework in discriminative learning of model parameters. In addition to all the necessary introduction of the background and tutorial material on the subject, we also included technical details on the derivation of the parameter optimization formulas for exponential-family distributions, discrete hidden Markov models (HMMs), and continuous-density HMMs in discriminative learning. Selected experimental results obtained by the authors in firsthand are presented to show that discriminative learning can lead to superior speech recognition performance over conventional parameter learning. Details on major algorithmic implementation issues with practical significance are provided to enable the practitioners to directly reduce the theory in the earlier part of the book into engineering practice.
530 ## - ADDITIONAL PHYSICAL FORM AVAILABLE NOTE
Additional physical form available note Also available in print.
588 ## - SOURCE OF DESCRIPTION NOTE
Source of description note Title from PDF t.p. (viewed on Oct. 24, 2008).
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element Automatic speech recognition
General subdivision Statistical methods.
690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN)
Topical term or geographic name as entry element Speech recognition.
690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN)
Topical term or geographic name as entry element Discriminative learning.
690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN)
Topical term or geographic name as entry element Optimization.
690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN)
Topical term or geographic name as entry element Growth transformation.
690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN)
Topical term or geographic name as entry element Hidden Markov model.
690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN)
Topical term or geographic name as entry element Exponential-family distribution.
700 1# - ADDED ENTRY--PERSONAL NAME
Personal name Deng, Li,
Dates associated with a name 1958-
730 0# - ADDED ENTRY--UNIFORM TITLE
Uniform title Synthesis digital library of engineering and computer science.
830 #0 - SERIES ADDED ENTRY--UNIFORM TITLE
Uniform title Synthesis lectures on speech and audio processing,
International Standard Serial Number 1932-1678 ;
Volume/sequential designation #4.
856 42 - ELECTRONIC LOCATION AND ACCESS
Materials specified Abstract with links to resource
Uniform Resource Identifier <a href="http://ieeexplore.ieee.org/servlet/opac?bknumber=6812876">http://ieeexplore.ieee.org/servlet/opac?bknumber=6812876</a>
Holdings
Withdrawn status Lost status Damaged status Not for loan Home library Current library Date acquired Total Checkouts Date last seen Price effective from Koha item type
        Indian Institute of Technology Delhi - Central Library Indian Institute of Technology Delhi - Central Library 22/08/2022   22/08/2022 22/08/2022 Ebooks
Copyright © 2022 Central Library, Indian Institute of Technology Delhi. All Rights Reserved.

Powered by Koha