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
Processing documents, character encoding schemes 69—70 Processing documents, interpreting characters 69—71 Productiveness property 15 Prominence 115—121 Prominence prediction 136—139 Prominence prediction, compound-noun phrases 136—137 Prominence prediction, data-driven approaches 138—139 Prominence prediction, function-word prominence 138 Prominence, data and labelling 119—121 Prominence, discourse prominence patterns 118—119 Prominence, emphatic prominence 119 Prominence, nuclear prominence 116 Prominence, prominence shift 117—118 Prominence, prominence systems 119—121 Prominence, syntactic prominence patterns 116—118 Pronunciation 192—224 see "Lexicons" Pronunciation about pronunciation 192—193 224 Pronunciation by analogy 220—221 Pronunciation, a phonological system for 197—207 Pronunciation, a phonological system for, about phonological system development 197 Pronunciation, a phonological system for, affricates 201 Pronunciation, a phonological system for, approximants/vowel combinations 201—202 Pronunciation, a phonological system for, difficult consonants 199—200 Pronunciation, a phonological system for, diphthongs 201 Pronunciation, a phonological system for, glides 201—202 Pronunciation, a phonological system for, inventory defining 203—204 Pronunciation, a phonological system for, minimal pairs principle/analysis 197—199 204 Pronunciation, a phonological system for, MRPA phoneme inventory 204—205 Pronunciation, a phonological system for, phoneme inventory 204—205 Pronunciation, a phonological system for, phoneme names 204—206 Pronunciation, a phonological system for, phonetic similarity principle 197—199 Pronunciation, a phonological system for, phonotactics/phonotactic grammar 207 Pronunciation, a phonological system for, rhotic/non-rhotic accents 202 Pronunciation, a phonological system for, simple consonants and vowels 197—199 Pronunciation, a phonological system for, syllabic issues 206—207 Pronunciation, a phonological system for, syllable boundaries 206 Pronunciation, a phonological system for, TIMIT phoneme inventory 203—204 Pronunciation, abstract phonological representations 196—197 Pronunciation, data sparsity problem 193 Pronunciation, language origin issues 223 Pronunciation, morphology 222—223 Pronunciation, names 223 Pronunciation, phonemic and phonetic input 193—194 Pronunciation, phonetic input problem 194—195 Pronunciation, post-lexical processing 223—224 Pronunciation, structured phonemic representation 195—196 Prosodic and verbal content 30—31 Prosodic hierarchy 114 Prosodic interaction 146 Prosodic meaning and function 122—127 Prosodic style 127 Prosody about prosody 14 Prosody in reading aloud 36—37 Prosody, affective 17 Prosody, augmentative 18 Prosody, determination from text 127—129 Prosody, determination from text, augmentative prosody control 128 Prosody, determination from text, prosody and human reading 127—129 Prosody, determination from text, prosody and synthesis techniques 128—129 Prosody, determination from text, TTS models 40 Prosody, null/neutral 18 Prosody, prediction from text 53 111—145 see "Prominence" "Prominence "Prosody Prosody, prediction from text, about prosody 111—112 144—145 Prosody, prediction from text, affective prosody 123—124 Prosody, prediction from text, augmentative prosody 125—126 142 Prosody, prediction from text, intonation and tune 121—122 Prosody, prediction from text, intonational-tune prediction 139 Prosody, prediction from text, labelling schemes/accuracy 139—141 Prosody, prediction from text, linguistic theories/prosody 141—142 Prosody, prediction from text, phrasing 112—115 Prosody, prediction from text, prosodic meaning and function 122—127 Prosody, prediction from text, prosodic phase structures 113 Prosody, prediction from text, prosodic style 127 Prosody, prediction from text, real dialogues 143—144 Prosody, prediction from text, speaker choice/variability 142—143 Prosody, prediction from text, suprasegmentality 124 Prosody, prediction from text, symbolic communication 126—127 Prosody, prediction from text, underspecified text 142 Pruning methods 508—509 Pruning methods, beam pruning 509 PSOLA see "Pitch-synchronous overlap and add (PSOLA) techniques" Punctuation and tokenisation 65—66 Punctuation, status markers 65 Punctuation, underlying punctuation 66 Pure unit selection 477 Quality improvements, future of 537 Radiation models for sound 330 Radiation models for sound, assumptions 338 Reading aloud 35—37 Reading aloud and silent reading 35—36 Reading aloud, prosody in 36—37 Reading aloud, style issues 37 Reading aloud, verbal content 37 RealSpeak system 514 Reduced stress 187 Redundancy, in speech 21 Reflection coefficients 366—367 Regression algorithms, F0 contour models 228 Resequencing algorithms 477 Residual analysis, for pitch detection 381 Residual manipulation 423 Residual speech signals 372—374 Residual speech signals, error signals 372 Residual speech signals, inverse filtering 372 Residual-excited linear prediction 421—424 Residual-excited linear prediction about residual excited LP 421—423 Residual-excited linear prediction, linear-prediction PSOLA 423—424 Residual-excited linear prediction, residual manipulation 423 Resonance 159 Resonance, formants 159—160 Resonance, resonant systems 311—313 Rhotic/non-rhotic accents 202 rVoice system 514 Scope and morphology 59 Second-generation synthesis systems 412—434 see "Residual-excited "Sinusoidal Second-generation synthesis systems about second-generation systems 412—413 433—434 Second-generation synthesis systems, cepstral coefficients, synthesis from 429—431 Second-generation synthesis systems, concatenation issues 431—432 Second-generation synthesis systems, diphone inventory creation 414 Second-generation synthesis systems, diphones from speech 414—415 Second-generation synthesis systems, MBROLA technique 429 Second-generation synthesis systems, speech units in 413—415 Secondary stress 187 segments 162 Semantics 16—17 Semiotic classification 45 79 92—94 Semiotic classification and translation 45—46 Semiotic classification, open-class rules 93 Semiotic classification, specialist sub-classifiers 93 Semiotic decoding 95 Semiotic systems 33—34 Semiotics 23 Sentences 14 62—63 Sentences, sentence splitting 53 67—68 Sentences, sentence-final prosody 67 Sentences, style manuals 68 Sentential stress 186—187 Sequence join classifier 503 Signal processing and unit-selection 511 Signal-to-signal TTS models 39 Signals and communication 13 see "Digital "Transforms" Sine function 277 Singular-value decomposition (SVD) 502 Sinusoid signals 263—265 Sinusoidal models techniques 424—429 Sinusoidal models techniques about sinusoidal models 424—425 Sinusoidal models techniques, harmonic/noise models (HNMs) 426—429 Sinusoidal models techniques, multi-band-excitation (MBE) 427 Sinusoidal models techniques, pure sinusoidal models 425—426 Sound Pattern of English, The (SPE) 181—182 Sound sources see "Speech production/articulatory phonetics" Sound, physics of 311—319 see Sound, physics of, acoustic capacitance 317 Sound, physics of, acoustic impedance 317 Sound, physics of, acoustic inductance 317 Sound, physics of, acoustic reflection 318 Sound, physics of, acoustic resistance 317 Sound, physics of, acoustic waves 316—318 Sound, physics of, boundary conditions 315 Sound, physics of, lossless tubes 317 Sound, physics of, resonant systems 311—313 Sound, physics of, sound propagation 317 Sound, physics of, speed of sound 316 Sound, physics of, standing waves 314 Sound, physics of, travelling waves 313—315 Source signal representations 372—379 Source signal representations, closed-phase analysis 374—377 Source signal representations, impulse/noise models 378 Source signal representations, open-phase analysis 377—378 Source signal representations, parameterisation of glotta-flow signals 379 Source signal representations, residual signals 372—374 Source-filter separation see "Cepstrum speech analysis" "Filter-bank "Linear-prediction Source-filter separation assumptions 338 Source/filter model of speech 151 SPE (The Sound Pattern of English) 181—182 Speaker choice/variability 142—143 Spectral analysis/frequency domain analysis 156 Spectral representations of speech, short term 343—345 Spectral representations of speech, short term, envelopes 345 Spectral-envelope 156—157 Spectral-envelope and vocal-tract representations 362—372 Spectrograms 157—159 Spectrograms in speech analysis 348—351 Speech acoustics 16 Speech production/articulatory phonetics 146—156 see "Glottis/glottal Speech production/articulatory phonetics about speech production 146—147 Speech production/articulatory phonetics, consonants 153—155 Speech production/articulatory phonetics, continuants 150 Speech production/articulatory phonetics, egressive pulmonic air stream 147 Speech production/articulatory phonetics, examining speech production 155—156 Speech production/articulatory phonetics, fundamental frequency (FO) 148 Speech production/articulatory phonetics, harmonics 148—149 Speech production/articulatory phonetics, larynx 148 Speech production/articulatory phonetics, neutral vowel sound 152—153 Speech production/articulatory phonetics, oral and nasal sounds 150 Speech production/articulatory phonetics, oral cavity 152 Speech production/articulatory phonetics, source/filter model of speech 151 Speech production/articulatory phonetics, stop sounds 150 Speech production/articulatory phonetics, timbre 149 Speech production/articulatory phonetics, unvoiced sounds 150 Speech production/articulatory phonetics, velum 150 Speech production/articulatory phonetics, vocal folds 148 Speech production/articulatory phonetics, vocal organs 147 Speech production/articulatory phonetics, vocal-tract filter 150—151 Speech production/articulatory phonetics, vowels 151—153 Speech recognition 1 22 Speech signals analysis 341—386 see "Epoch "Filter-bank "Linear-prediction "Pitch "Source Speech signals analysis about speech analysis 341 384—386 Speech signals analysis, short term 341—352 Speech signals analysis, short term, auditory scales 351—352 Speech signals analysis, short term, envelopes 345 Speech signals analysis, short term, equivalent rectangular bandwidth (ERB) scale 352 Speech signals analysis, short term, frame lengths and shifts 345—349 Speech signals analysis, short term, mel-scale 351 Speech signals analysis, short term, pitch-asynchronous analysis 347 Speech signals analysis, short term, pitch-synchronous analysis 347 Speech signals analysis, short term, spectral representations 343—345 Speech signals analysis, short term, spectrograms 348—351 Speech signals analysis, short term, time-frequency tradeoff 346 Speech signals analysis, short term, windowing 342—345 Speech signals analysis, spectral-envelope and vocal-tract representations 362—372 Speech synthesis markup language (SSML) 69 Speech technology/linguistics relationship 533—536 Speech technology/linguistics relationship, future of 537—538 Speech, communicative use principles 160—172 Speech, communicative use principles, about communicating with speech 161—162 Speech, communicative use principles, allophones 162 Speech, communicative use principles, allophonic variation 166—167 Speech, communicative use principles, aspiration 168 Speech, communicative use principles, assimilation effect 167 Speech, communicative use principles, coarticulation 168 Speech, communicative use principles, colouring effect 167 Speech, communicative use principles, continuous nature issues 169—170 Speech, communicative use principles, distinctiveness issues 171—172 Speech, communicative use principles, IPA alphabet 163—165 Speech, communicative use principles, minimal pair 163 Speech, communicative use principles, modified timit ascii character set 166 Speech, communicative use principles, nasalisation colouring 167 Speech, communicative use principles, phonemes 161—164 Speech, communicative use principles, phones 162—164 Speech, communicative use principles, phonetic context 167 Speech, communicative use principles, segments 162 Speech, communicative use principles, targets 168—169 Speech, communicative use principles, transcriptions 170—171 Speech, disfluences in 30 Speech, redundancy in 21 Speech/writing comparisons 26—35 Speech/writing comparisons, component balance 31—32 Speech/writing comparisons, form comparisons 28—29 Speech/writing comparisons, non-linguistic contents 32—33 Speech/writing comparisons, number-communication systems 33 Speech/writing comparisons, physical natures of 27—28 Speech/writing comparisons, prosodic and verbal contents 30—31 Speech/writing comparisons, semiotic systems 33—34 Speech/writing comparisons, speech spontaneity 30 Speech/writing comparisons, usage of each 29—30 Speed of sound 316 Splicing costs 499 Spoken text markup language 69 Standard deviation 436 standing waves 314 Statistical parsing 105 Status markers 65 Stochastic signals 288 Stop sounds 150 Stress in speech 116 Stress in speech, lexical stress 116 186—189 Stress in speech, metrical stress 188 Stress in speech, reduced stress 187 Stress in speech, secondary stress 187 Stress in speech, sentential stress 186—187 Strict layer hypothesis 114 Style manuals 68 Sum of random variables 545—546 Sums-of-products model 257—258 Superimpositional intonation models 242 Superposition of functional contours (SFC) model 254 Support-vector machines 221 Suprasegmentality 124 Syllables 184—186 Syllables, boundaries 206 Syllables, syllabic consonants 184 Syllables, syllabic writing 34 Symbolic language/communication 10—12 126—127 Symbolic language/communication, combinations of symbols 11—12 Synonyms 57—58 Syntactic ambiguity 46—47 Syntactic analysis 102 Syntactic hierarchy 16 Syntactic homonyms 88—9 Syntactic phrases 16 Syntactic prominence patterns 116—18 Syntactic trees 102 Syntax 16 Synthesis see also "Classical linear-prediction (LP) synthesis" "Formant "Hidden synthesis "Second-generation "Vocal-tract synthesis Synthesis of prosody see "Autosegmental-metrical (AM) intonation model" "Data-driven "Deterministic synthesis "Intonation "Timing Synthesis, articulatory synthesis 405—407 Synthesis, synthesis algorithms, future of 536—537 Synthesis, synthesis specification 387—388 System lexicon 214—215
Ðåêëàìà
|
|
Î ïðîåêòå