000 04413nam a22005175i 4500
001 978-3-031-02557-0
003 DE-He213
005 20240730164002.0
007 cr nn 008mamaa
008 220601s2008 sz | s |||| 0|eng d
020 _a9783031025570
_9978-3-031-02557-0
024 7 _a10.1007/978-3-031-02557-0
_2doi
050 4 _aTK1-9971
072 7 _aTHR
_2bicssc
072 7 _aTEC007000
_2bisacsh
072 7 _aTHR
_2thema
082 0 4 _a621.3
_223
100 1 _aHe, Xiadong.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_981500
245 1 0 _aDiscriminative Learning for Speech Recognition
_h[electronic resource] :
_bTheory and Practice /
_cby Xiadong He, Li Deng.
250 _a1st ed. 2008.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2008.
300 _aVII, 112 p.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aSynthesis Lectures on Speech and Audio Processing,
_x1932-1678
505 0 _aIntroduction and Background -- Statistical Speech Recognition: A Tutorial -- Discriminative Learning: A Unified Objective Function -- Discriminative Learning Algorithm for Exponential-Family Distributions -- Discriminative Learning Algorithm for Hidden Markov Model -- Practical Implementation of Discriminative Learning -- Selected Experimental Results -- Epilogue -- Major Symbols Used in the Book and Their Descriptions -- Mathematical Notation -- Bibliography.
520 _aIn 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 reproduce the theory in the earlier part of the book into engineering practice. Table of Contents: Introduction and Background / Statistical Speech Recognition: A Tutorial / Discriminative Learning: A Unified Objective Function / Discriminative Learning Algorithm for Exponential-Family Distributions / Discriminative Learning Algorithm for Hidden Markov Model / Practical Implementation of Discriminative Learning / Selected Experimental Results / Epilogue / Major Symbols Used in the Book and Their Descriptions / Mathematical Notation / Bibliography.
650 0 _aElectrical engineering.
_981501
650 0 _aSignal processing.
_94052
650 0 _aAcoustical engineering.
_99499
650 1 4 _aElectrical and Electronic Engineering.
_981502
650 2 4 _aSignal, Speech and Image Processing.
_931566
650 2 4 _aEngineering Acoustics.
_931982
700 1 _aDeng, Li.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_981503
710 2 _aSpringerLink (Online service)
_981504
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783031014291
776 0 8 _iPrinted edition:
_z9783031036859
830 0 _aSynthesis Lectures on Speech and Audio Processing,
_x1932-1678
_981505
856 4 0 _uhttps://doi.org/10.1007/978-3-031-02557-0
912 _aZDB-2-SXSC
942 _cEBK
999 _c85187
_d85187