Furui S. — Digital Speech Processing, Synthesis, and Recognition :: Электронная библиотека попечительского совета мехмата МГУ

Главная Ex Libris Книги Журналы Статьи Серии Каталог Wanted Загрузка ХудЛит Справка Поиск по индексам Поиск Форум

Авторизация

Поиск по указателям

Furui S. — Digital Speech Processing, Synthesis, and Recognition

Обсудите книгу на научном форуме

Нашли опечатку?
Выделите ее мышкой и нажмите Ctrl+Enter

Название: Digital Speech Processing, Synthesis, and Recognition

Автор: Furui S.

Аннотация:

A study of digital speech processing, synthesis and recognition. This second edition contains new sections on the international standardization of robust and flexible speech coding techniques, waveform unit concatenation-based speech synthesis, large vocabulary continuous-speech recognition based on statistical pattern recognition, and more.

Язык:

Рубрика: Наука/

Статус предметного указателя: Готов указатель с номерами страниц

ed2k: ed2k stats

Издание: 2-nd

Год издания: 2000

Количество страниц: 452

Добавлена в каталог: 03.03.2007

Операции: Положить на полку | Скопировать ссылку для форума | Скопировать ID

Предметный указатель

Hidden Markov model (HMM), discrete      279
Hidden Markov model (HMM), ergodic      279 305
Hidden Markov model (HMM), ergodic based method      371
Hidden Markov model (HMM), hidden state sequence, hidden state sequence uncovering problem      283
Hidden Markov model (HMM), MCE/GPD training of      292 335
Hidden Markov model (HMM), mixture autoregressive (AR)      371
Hidden Markov model (HMM), MMI training of      292
Hidden Markov model (HMM), problems, procedures, semicontinuous      292
Hidden Markov model (HMM), system for word recognition      293
Hidden Markov model (HMM), theory and implementation of      278
Hidden Markov model (HMM), three basic algorithms for      282
Hidden Markov model (HMM), tied mixture      292
Hidden Markov model (HMM), training problem      283
Hidden nodes      399
Hierarchy model      308
High-emphasis filter      102
Homomorphic analysis      66
Homomorphic filtering      66
Homomorphic prediction      129
Huffman coding      133
Human-computer dialog systems      323
Human-computer interaction      243
Hybrid coding      135 187
IBM      325
Impostor      354
Individual characteristics      349 351
Individual differences, acquired      351
Individual differences, hereditary      351
Individuality      246
Information rate distortion theory      134 177
Information transmission theory      313
Initial state distribution      281
Input and output nodes      399
Integer band sampling      162
Intelligibility test      200
Inter-session (temporal) variability      360
Internal thresholds      399
Interpolation characteristics      126
Intonation      7 10
Intonation, component, basic      230
Intraspeaker variation      360 364
Inverse filter      85 255
Inverse filter, first- or second-order critical damping      361
Inverse filtering method      93 114
Irreversible coding      133
Island-driven method      311
Isolated word recognition      246
Itakura — Saito distance (distortion)      254
Jaw      9
K-means algorithm (Lloyd's algorithm)      176 394
K-nearest neighbor (KNN) method      332
Karhunen — Loeve Transform (KLT)      163
Katz's backoff smoothing      317
Kelly's speech synthesis (production) model      37 110
Knockout method      363
Knowledge processing, advanced      382
Knowledge source      308 382
Lag window      252
Language model      314 344
Large-vocabulary continuous speech recognition      306
Larynx      9
Lattice      248
Lattice diagram      285
Lattice filter      109
LBG algorithm (cluster-splitting method)      176 395
LD-CELP      205
Left-to-right method      311
Level building (LB) method      298
Lexicon      306
Lifter      77 261
Likelihood      248 282
Likelihood normalization      364
Likelihood ratio      347 363 364
LIMSI      324
Line spectrum pair (LSP)      116
Line spectrum pair (LSP) analysis      116
Line spectrum pair (LSP) analysis parameters      121
Line spectrum pair (LSP) analysis parameters, coding of      126
Line spectrum pair (LSP) analysis, principle of      116
Line spectrum pair (LSP) analysis, solution of      119
Line spectrum pair (LSP) synthesis filter      122
Linear delta modulation (LDM)      149
Linear PCM      142
Linear prediction      2 83 145
Linear predictive coding (LPC)      2 78
Linear predictive coding (LPC) analysis      68 83 250 252
Linear predictive coding (LPC) analysis, procedure      86
Linear predictive coding (LPC) methods, code-excited      138
Linear predictive coding (LPC) methods, multi-pulse-excited      138
Linear predictive coding (LPC) methods, residual-excited      138 187
Linear predictive coding (LPC) methods, speech-excited      138 187
Linear predictive coding (LPC) parameters, mutual relationships between      127
Linear predictive coding (LPC) speech synthesizer      228
Linear predictor coefficients      84
Linear predictor filter      84
Linear transformation      335
Linear transformation based on multiple regression analysis      336
Linearly separable equivalent circuit      30 64 73 85
Linguistic constraints      246
Linguistic information      5 243
Linguistic knowledge      246
Linguistic science, new      383
Linguistic units      381
Lip rounding      12
Lips      9
Littering      65
Lloyd's algorithm (K-means algorithm)      176 394
Local decoder      145
Locus theory      229
Log likelihood ratio distance      255
Log PCM      142
Lombard effect      341
Long-term (pitch) prediction      148 153
Long-term (term) averaged speech spectrum (LAS)      23 370
Long-term-statistics-based method      368
Loss heat conduction      32
Loss, leaky      32
Loss, viscous      32
Loudness      230
LPC cepstral coefficients      257
LPC cepstral distance      257
LPC cepstrum      69
LPC correlation coefficients      260
LPC correlation function      127
LSI for speech processing use      386
Lungs      89
M-L method      173
Markov chains      279
Markov sources      279
Mass conservation equation      32
Matched filter principle      197
Matrix quantization (MQ)      138 182 337
Maximum a posteriori (MAP)      330
Maximum a posteriori (MAP) decoding rule      314
Maximum a posteriori (MAP) estimates      335
Maximum a posteriori (MAP) probability      313
Maximum likelihood (ML) estimation      293
Maximum likelihood (ML) method      70 254
Maximum likelihood (ML) spectral distance      254
Maximum likelihood (ML) spectral estimation      89
Maximum likelihood (ML) spectral estimation, formulation of      89
Maximum likelihood (ML) spectral estimation, physical meaning of      93
MDL (Minimum Description Length) criterion      325
Mean Opinion Score (MOS)      200
Mel frequency cepstral coefficient (MFCC)      252
Mel-scale frequency axis      251
Mimicked voice      352
Minimum phase impulse response      77
Minimum residual energy      256
Mismatches, acoustic      341

Mismatches, linguistic      341
MITalk-79 system      234
Mixed excitation LPC (MELP)      196
Mixture      290
MLLR (maximum likelihood linear regression) method      325 330
Models      244
Modified correlation method      79
Modified, autocorrelation function      14 98 107
Momentum equation      32
Morph      234
Morphemes      317
Morphological analysis      317
Multi-pulse-excited LPC (MPC)      189
Multiband excitation (MBE)      196
Multilayer perceptrons      399
Multipath search coding      173
multiple regression analysis      336
Multistage processing      178
Multistage VQ      179
Multitemplate method      332
Multivariate autoregression (MAR)      370
Mutual information      292
N-best based adaptation      339
N-best hypotheses      339
N-best results      312
N-gram language model      316
Nasal      11
Nasal cavity      9
Nasalization      11
Nasalized vowel      11
Nearest-neighbor selection rule      394
network model      310
Neural net      399
Neutral vowel      13
Neyman — Pearson hypothesis testing formulation      305
Neyman — Pearson lemma      347
Noise, additive      341
Noise, shaping      138 156
Noise, source      44
Noise, threshold      135
Nonlinear quantization      138
Nonlinear warping of the spectrum      335
Nonparametric analysis (NPA)      52
Nonspeech sounds      249
Nonuniform sampling      266
Normal equation      89
Normalized residual energy      256
Nyquist rate      47
Objective evaluation      200
Observation probability      281
Observation probability distribution      281
Opinion tests      200
Opinion-equivalent SNR (SNRq)      200
Optimal (minimum-distortion) quantizer      394
Oral cavity      9
Orthogonal polynomial representation      367
Out-of-vocabulary      305 344
Pair comparison (A-B test)      200
Parallel connection      225
Parallel model combination (PMC)      344 363
Parametric analysis (PA)      52
PARCOR (partial autocorrelation) analysis      102
PARCOR (partial autocorrelation) analysis, formulation of      102
PARCOR (partial autocorrelation) analysis-synthesis system      110
PARCOR (partial autocorrelation) and LPC coefficients, relationship between      108
PARCOR (partial autocorrelation) coefficient      102
PARCOR (partial autocorrelation) coefficient, extraction process      89
PARCOR (partial autocorrelation) synthesis filter      109
Partial correlator      107
Peak factor      21
Peak-weighted distance      258
Perceiving dynamic signals      385
Perceptual units      381
Perceptually-based weighting      192
Periodogram      92
Perplexity      322
Perplexity log      322
Perplexity test-set      322
Pharynx      9
Phase equalization      195
Phone      6
Phoneme context      238
Phoneme reference template      275
Phoneme, 6      247
Phoneme-based algorithm      247
Phoneme-based system      229
Phoneme-based word recognition      275
Phoneme-like templates      277
Phonemic symbol      6
Phonetic decision tree      320
Phonetic information      246
Phonetic invariants      331
Phonetic symbol      6
Phonocode method      184
Phrase component      230
Physical units      382
Pitch      10 264
Pitch (long-term) prediction      148 153
Pitch error, double      79
Pitch error, half      79
Pitch extraction      78
Pitch extraction by correlation processing      79
Pitch extraction by spectral processing      79
Pitch extraction by waveform processing      79
Pitch-synchronous waveform concatenation      220
Plosive      10
Pole-zero analysis      127
Pole-zero analysis by maximum likelihood estimation      130
Polynomial coefficients      367
Polynomial expansion coefficients, lower order      262
Positive definiteness      250
Postfilter, adaptive noise-shaping      158
Postfiltering      158
Pragmatics      264 308
Predicate logic      312
Prediction      145
Prediction error      102
Prediction error operators, forward and backward      106
Prediction gain      147
Prediction residual      141 145 256
Predictive coding      141 143
Preemphasis      51
Procedural knowledge representation      312
Production model      383
Production system      312
Progressing wave model      32
Prosodic features      379
Prosodic features, control of      230
Prosodics      308
Prosody      264
Pseudophoneme      277
PSI-CELP      205
Pulse code modulation (PCM)      138 141
Pulse generator      27
Quadrature mirror filter (QMF)      162
Quantization      47
quantization distortion      49 177
Quantization error      49
Quantization noise      49
Quantization step size      47
Quantizing      45
Quefrency      64
Quefrency-weighted cepstral distance measure      262
Radiation      9 27
Random learning      176
Rate distortion function      135
Receiver operating characteristic (ROC) curve      354
Recognition, speaker      349
Recognition, speech      243
Rectangular window      58

1 2 3

О проекте