LEADER 05673nam 22007334a 450 001 9911019863803321 005 20200520144314.0 010 $a9786610275120 010 $a9781280275128 010 $a128027512X 010 $a9780470020913 010 $a0470020911 010 $a9780470020906 010 $a0470020903 035 $a(CKB)1000000000356175 035 $a(EBL)232683 035 $a(OCoLC)70110497 035 $a(SSID)ssj0000199141 035 $a(PQKBManifestationID)11188037 035 $a(PQKBTitleCode)TC0000199141 035 $a(PQKBWorkID)10184482 035 $a(PQKB)10691831 035 $a(MiAaPQ)EBC232683 035 $a(Perlego)2763795 035 $a(EXLCZ)991000000000356175 100 $a20041116d2005 uy 0 101 0 $aeng 135 $aur|n|---||||| 181 $ctxt 182 $cc 183 $acr 200 10$aMathematical models for speech technology /$fStephen E. Levinson 210 $aChichester, West Sussex, England ;$aHoboken, NJ, USA $cJohn Wiley$dc2005 215 $a1 online resource (283 p.) 300 $aDescription based upon print version of record. 311 08$a9780470844076 311 08$a0470844078 320 $aIncludes bibliographical references (p. [243]-255) and index. 327 $aMathematical Models for Speech Technology; Contents; Preface; 1 Introduction; 1.1 Milestones in the history of speech technology; 1.2 Prospects for the future; 1.3 Technical synopsis; 2 Preliminaries; 2.1 The physics of speech production; 2.1.1 The human vocal apparatus; 2.1.2 Boundary conditions; 2.1.3 Non-stationarity; 2.1.4 Fluid dynamical effects; 2.2 The source-filter model; 2.3 Information-bearing features of the speech signal; 2.3.1 Fourier methods; 2.3.2 Linear prediction and the Webster equation; 2.4 Time-frequency representations; 2.5 Classification of acoustic patterns in speech 327 $a2.5.1 Statistical decision theory2.5.2 Estimation of class-conditional probability density functions; 2.5.3 Information-preserving transformations; 2.5.4 Unsupervised density estimation - quantization; 2.5.5 A note on connectionism; 2.6 Temporal invariance and stationarity; 2.6.1 A variational problem; 2.6.2 A solution by dynamic programming; 2.7 Taxonomy of linguistic structure; 2.7.1 Acoustic phonetics, phonology, and phonotactics; 2.7.2 Morphology and lexical structure; 2.7.3 Prosody, syntax, and semantics; 2.7.4 Pragmatics and dialog; 3 Mathematical models of linguistic structure 327 $a3.1 Probabilistic functions of a discrete Markov process3.1.1 The discrete observation hidden Markov model; 3.1.2 The continuous observation case; 3.1.3 The autoregressive observation case; 3.1.4 The semi-Markov process and correlated observations; 3.1.5 The non-stationary observation case; 3.1.6 Parameter estimation via the EM algorithm; 3.1.7 The Cave-Neuwirth and Poritz results; 3.2 Formal grammars and abstract automata; 3.2.1 The Chomsky hierarchy; 3.2.2 Stochastic grammars; 3.2.3 Equivalence of regular stochastic grammars and discrete HMMs; 3.2.4 Recognition of well-formed strings 327 $a3.2.5 Representation of phonology and syntax4 Syntactic analysis; 4.1 Deterministic parsing algorithms; 4.1.1 The Dijkstra algorithm for regular languages; 4.1.2 The Cocke-Kasami-Younger algorithm for context-free languages; 4.2 Probabilistic parsing algorithms; 4.2.1 Using the Baum algorithm to parse regular languages; 4.2.2 Dynamic programming methods; 4.2.3 Probabilistic Cocke-Kasami-Younger methods; 4.2.4 Asynchronous methods; 4.3 Parsing natural language; 4.3.1 The right-linear case; 4.3.2 The Markovian case; 4.3.3 The context-free case; 5 Grammatical Inference 327 $a5.1 Exact inference and Gold's theorem5.2 Baum's algorithm for regular grammars; 5.3 Event counting in parse trees; 5.4 Baker's algorithm for context-free grammars; 6 Information-theoretic analysis of speech communication; 6.1 The Miller et al. experiments; 6.2 Entropy of an information source; 6.2.1 Entropy of deterministic formal languages; 6.2.2 Entropy of languages generated by stochastic grammars; 6.2.3 Epsilon representations of deterministic languages; 6.3 Recognition error rates and entropy; 6.3.1 Analytic results derived from the Fano bound; 6.3.2 Experimental results 327 $a7 Automatic speech recognition and constructive theories of language 330 $aMathematical Models of Spoken Language presents the motivations for, intuitions behind, and basic mathematical models of natural spoken language communication. A comprehensive overview is given of all aspects of the problem from the physics of speech production through the hierarchy of linguistic structure and ending with some observations on language and mind. The author comprehensively explores the argument that these modern technologies are actually the most extensive compilations of linguistic knowledge available.Throughout the book, the emphasis is on placing all the material in 606 $aSpeech processing systems 606 $aComputational linguistics 606 $aApplied linguistics$xMathematics 606 $aStochastic processes 606 $aKnowledge, Theory of 615 0$aSpeech processing systems. 615 0$aComputational linguistics. 615 0$aApplied linguistics$xMathematics. 615 0$aStochastic processes. 615 0$aKnowledge, Theory of. 676 $a006.4/54/015118 700 $aLevinson$b Stephen E$0157418 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9911019863803321 996 $aMathematical models for speech technology$94423046 997 $aUNINA