Àâòîðèçàöèÿ
Ïîèñê ïî óêàçàòåëÿì
Taylor P. — Text-to-Speech Synthesis
Îáñóäèòå êíèãó íà íàó÷íîì ôîðóìå Íàøëè îïå÷àòêó?
Íàçâàíèå: Text-to-Speech SynthesisÀâòîð: Taylor P. Àííîòàöèÿ: Text-to-Speech Synthesis provides a complete, end-to-end account of the process of generating speech by computer. Giving an in-depth explanation of all aspects of current speech synthesis technology, it assumes no specialized prior knowledge. Introductory chapters on linguistics, phonetics, signal processing and speech signals lay the foundation, with subsequent material explaining how this knowledge is put to use in building practical systems that generate speech. Including coverage of the very latest techniques such as unit selection, hidden Markov model synthesis, and statistical text analysis, explanations of the more traditional techniques such as format synthesis and synthesis by rule are also provided. Weaving together the various strands of this multidisciplinary field, the book is designed for graduate students in electrical engineering, computer science, and linguistics. It is also an ideal reference for practitioners in the fields of human communication interaction and telephony.
ßçûê: Ðóáðèêà: Computer science /Ñòàòóñ ïðåäìåòíîãî óêàçàòåëÿ: Ãîòîâ óêàçàòåëü ñ íîìåðàìè ñòðàíèö ed2k: ed2k stats Ãîä èçäàíèÿ: 2009Êîëè÷åñòâî ñòðàíèö: 597Äîáàâëåíà â êàòàëîã: 31.10.2010Îïåðàöèè: Ïîëîæèòü íà ïîëêó |
Ñêîïèðîâàòü ññûëêó äëÿ ôîðóìà | Ñêîïèðîâàòü ID
Ïðåäìåòíûé óêàçàòåëü
System testing 523 Tagging 82—83 Talking-head synthesis 406—407 527 see Targets 168—169 Tests/testing 523—526 Tests/testing, Blizzard Challenge testing 526 Tests/testing, comparison tests 524 Tests/testing, competitive evaluations 526 Tests/testing, Harvard sentences 523 Tests/testing, Haskins sentences 523 Tests/testing, modified rhyme test (MRT) 523 524 Tests/testing, naturalness tests 524 Tests/testing, semantically unpredictable sentences 523 Tests/testing, system testing 523 Tests/testing, test data 525 Tests/testing, unit/component testing 525—526 Tests/testing, word-recognition tests 523—524 Text analysis, future of 536 Text anomalies 105 Text decoding/analysis 22 52—53 78—110 see "Non-natural-language "Text-classification Text decoding/analysis about text decoding 78—79 105—110 Text materials 518 Text normalisation 44 106 Text segmentation and organisation 63—68 see "Processing "Sentences" "Words" Text segmentation and organisation, about text segmentation 52—53 75—77 Text segmentation and organisation, sentence splitting 67—68 Text segmentation and organisation, tokenisation 64—67 Text-as-language TTS models 39 Text-classification algorithms 79—92 Text-classification algorithms, ad-hoc approaches 83 Text-classification algorithms, bag-of-features approach 84 Text-classification algorithms, cluster impurity 88 Text-classification algorithms, collocation rule 84 Text-classification algorithms, context-sensitive rewrite rule 83—84 Text-classification algorithms, curse of dimensionality 81 534 Text-classification algorithms, data driven approach 80 Text-classification algorithms, decision lists 85—86 Text-classification algorithms, decision trees 87—88 Text-classification algorithms, deterministic rule approaches 83 Text-classification algorithms, engine/rule separation 83 Text-classification algorithms, features and algorithms 79—82 Text-classification algorithms, hidden Markov model (HMM) 89—91 Text-classification algorithms, naive Bayes' classifier 86—87 Text-classification algorithms, part-of-speech (POS) tagging 82 88—92 Text-classification algorithms, probabilistic approach 80 Text-classification algorithms, statistical approach 80 Text-classification algorithms, tagging 82—83 Text-classification algorithms, trigger tokens 84—85 Text-classification algorithms, unsupervised approach 80 Text-classification algorithms, word-sense disambiguation (WSB) 82—83 Text-to-speech (TTS) see also "Models of TTS" "Problems Text-to-speech (TTS) about text-to-speech 1—2 26 50—51 Text-to-speech (TTS), basic principles 41 Text-to-speech (TTS), common-form model 5—6 Text-to-speech (TTS), development goals 3 Text-to-speech (TTS), engineering approach 4 Text-to-speech (TTS), intelligibility issues 3 Text-to-speech (TTS), naturalness issues 3 Text-to-speech (TTS), purposes 2 Texture mapping 528 Third-generation techniques see "Hidden Markov model (HMM)" "Unit-selection Tilt intonation model, analysis with 250 Tilt intonation model, synthesis with 227 242—244 249—250 Time invariance, assumptions concerning 337 Time-domain PSOLA (TD-PSOLA) 416—417 Time-domain PSOLA (TD-PSOLA), pitch-scale modification 416—417 Time-domain PSOLA (TD-PSOLA), time-scale modification 416 Time-frequency tradeoff, in speech analysis 346 Timing issues 254—259 Timing issues about timing 254—255 Timing issues, Campbell model 258 Timing issues, durations 254 Timing issues, Klatt rules 256—257 Timing issues, nature of timing 255—256 Timing issues, phase-final lengthening 256 Timing issues, sums-of-products model 257—258 TIMIT phoneme inventory 203—206 553 TIMIT phoneme inventory, modified timit ascii character set 166 ToBI intonation scheme 237 247 248 Toeplitz matrix 361 Token, definition 54 Tokenisation 53 64—67 Tokenisation and punctuation 65—66 Tokenisation, tokenisation algorithms 66—67 Tone languages 124 227 Tonemes 121 transcriptions 170—171 Transfer-function poles 364—365 transforms 284—288 307 see Transforms about transforms 284 Transforms, analytical analysis 287 Transforms, convolution 287 Transforms, duality for time and frequency 284—285 Transforms, frequency shift 286 Transforms, impulse properties 285 Transforms, Laplace transform 283 Transforms, linearity 284 Transforms, modulation 286 Transforms, numerical analysis 287 transforms, scaling 285 Transforms, stochastic signals 288 Transforms, time delay 286 Transforms, z-transform 282—283 Translation from semiotic classification 45—46 Tree-banks 105 Trigger tokens 84—85 Triphone models 451 Tune and intonation 121—122 Understanding 19 22—23 Uniform distribution 549 Unit back-off searching 505—508 Unit back-off solution 505—506 Unit-selection databases 517—518 Unit-selection databases, speaker choice issues 518 Unit-selection synthesis 474—516 see Unit-selection synthesis about unit selection synthesis 251—252 474—479 510—511 515—516 Unit-selection synthesis, ATR family contribution 512—514 Unit-selection synthesis, CHATR system 513 Unit-selection synthesis, concatenation of units 477 Unit-selection synthesis, coverage 510 Unit-selection synthesis, extending from concatenative synthesis 475—477 Unit-selection synthesis, features 479—484 Unit-selection synthesis, features, base types 479—410 Unit-selection synthesis, features, cost and perception 511—512 Unit-selection synthesis, features, dimensionality reduction/accuracy tradeoff 483 Unit-selection synthesis, features, feature choosing 481—482 Unit-selection synthesis, features, feature combination structures 481 Unit-selection synthesis, features, feature types 482—484 Unit-selection synthesis, features, hand labelling technique 480—481 Unit-selection synthesis, features, heterogeneous systems 480 Unit-selection synthesis, features, homogeneous systems 480 Unit-selection synthesis, features, intelligibility issue 510 Unit-selection synthesis, features, join feature structure 481 Unit-selection synthesis, features, left/right join feature structure 481 Unit-selection synthesis, features, linguistic and acoustic features 480—481 Unit-selection synthesis, features, naturalness issues 510 Unit-selection synthesis, features, non-uniform unit synthesis 480 Unit-selection synthesis, features, original/derived features 481 Unit-selection synthesis, features, partial synthesis 482 Unit-selection synthesis, features, script technique 480 Unit-selection synthesis, features, target feature structure 481 Unit-selection synthesis, HMM system 514 Unit-selection synthesis, Hunt and Black algorithm 477—479 Unit-selection synthesis, Laureate system 513 Unit-selection synthesis, NextGen system (AT&T) 513—514 Unit-selection synthesis, principle of least modification 477 Unit-selection synthesis, pure unit selection 477 Unit-selection synthesis, RealSpeak system 514 Unit-selection synthesis, resequencing algorithms 477 Unit-selection synthesis, rVoice system 514 Unit-selection synthesis, searching 504—509 Unit-selection synthesis, searching about searching 504—505 Unit-selection synthesis, searching, beam pruning 509 Unit-selection synthesis, searching, diphone unit-selection system 505 Unit-selection synthesis, searching, half-phone solution 506—507 Unit-selection synthesis, searching, Hunt and Black algorithm 504 Unit-selection synthesis, searching, multi-pass searching 509 Unit-selection synthesis, searching, pre-selection 508—509 Unit-selection synthesis, searching, pruning methods 508—509 Unit-selection synthesis, searching, Viterbi algorithm/search 504—505 508 Unit-selection synthesis, signal processing issues 511 Unit-selection synthesis, target function formulation 484—493 Unit-selection synthesis, target function formulation, about the target function 484—485 Unit-selection synthesis, target function formulation, acoustic-space formulation (ASF) 485 493—497 Unit-selection synthesis, target function formulation, context-orientated-clustering 495 Unit-selection synthesis, target function formulation, decision-tree clustering 494—496 Unit-selection synthesis, target function formulation, disruption issues 485 Unit-selection synthesis, target function formulation, distance/cost issues 484 Unit-selection synthesis, target function formulation, equal-error-rate approach to learning 491 Unit-selection synthesis, target function formulation, Euclidean distance 486 Unit-selection synthesis, target function formulation, feature axis scaling 488 Unit-selection synthesis, target function formulation, full set of candidates 484 Unit-selection synthesis, target function formulation, general partial-synthesis functions 496—497 Unit-selection synthesis, target function formulation, hand tuning 491 Unit-selection synthesis, target function formulation, independent feature formulation (IFF) 485—488 Unit-selection synthesis, target function formulation, independent-feature formulation limitations 491—493 Unit-selection synthesis, target function formulation, Manhattan distance 486 Unit-selection synthesis, target function formulation, perceptual approaches 490—491 Unit-selection synthesis, target function formulation, perceptual space formulating/defining 485—486 Unit-selection synthesis, target function formulation, perceptual substitutability principle 485 Unit-selection synthesis, target function formulation, search candidates set 484 Unit-selection synthesis, target function formulation, target weights setting 488—491 Unit/component testing 525—6 Unknown words, decoding 98 Unknown words, problems with 216—218 Unvoiced sounds 150 UTF-16 71 UTF-8 71 Utterance structure 71 Variance 436 Velum 150 Verb-balancing rule 131 Verbal communication 14—16 Verbal communication, arbitraryness 15 Verbal communication, discreteness 15—16 Verbal communication, duality 15 Verbal communication, phonemes 14 Verbal communication, productiveness 15 Verbal communication, sentences 14 Verbal communication, words 14 Verbalisation 95—97 Visemes 528 Viterbi algorithm 92 444—448 504—505 508 Vocal organs 147 Vocal-tract and spectral-envelope representations 362—372 Vocal-tract models, synthesis with 387—411 see "Classical "Formant "Residual-excited "Vowel-tube Vocal-tract models, synthesis with, about synthesis with vocal-tract models 387 407—411 Vocal-tract models, synthesis with, ease of data acquisition 407 Vocal-tract models, synthesis with, effectiveness of models 407 Vocal-tract models, synthesis with, modularity issues 407 Vocal-tract models, synthesis with, synthesis specification 387—388 Vocal-tract, filter 150—151 Vocal-tract, sound loss models 335—336 Vocal-tract, straight tube assumptions 337 Vocal-tract, transfer function 310—311 Voice transformation, and synthesizing emotion 530 VoiceXML 69 Vowel sounds 151—153 Vowel sounds, diphthongs 153 Vowel sounds, monophthongs 153 Vowel sounds, neutral vowel 152 Vowel-tube models 319—330 Vowel-tube models about the vowel tube 319 Vowel-tube models, all-pole resonator model 329—330 Vowel-tube models, discrete time and distance 320 Vowel-tube models, junction of two tubes 320—322 Vowel-tube models, junction special cases 322—323 Vowel-tube models, multi-tube vocal-tract model 327—329 Vowel-tube models, reflection coefficient 322 Vowel-tube models, single-tube vocal-tract model 325—327 Vowel-tube models, transmission coefficient 322 Vowel-tube models, two-tube vocal-tract model 323—325 Windowing 342—345 Word formation/lexical phonology 179—181 Word variants 57 Word-recognition tests 523—524 Word-sense disambiguation (WSB) 82—83 Words 14 Words, ambiguity issues 54 Words, defining in TTS 55—59 Words, definitions/terminology 54—55 Words, form issues 53—54 Words, hyphenated forms 61—62 Words, shortened forms 61 Words, slang forms 61 Writing see "Speech/writing comparisons" writing systems 34—35 Writing systems, Abjab 34—35 Writing systems, alphabetic 34 Writing systems, logographic 34 Writing systems, pictographic 34 Writing systems, syllabic 34 z-transform 282—283 z-transform and digital filters 293—294 297—298
Ðåêëàìà
|
|
Î ïðîåêòå