Dynamic Speech Models: Theory, Algorithms, and Applications
Speech dynamics refer to the temporal characteristics in all stages of the human speech communication process. This speech starts with the formation of a linguistic message in a speaker's brain and ends with the arrival of the message in a listener's brain. Given the intricacy of the dynamic speech process and its fundamental importance in human communication, this monograph is intended to provide a comprehensive material on mathematical models of speech dynamics and to address the following issues: How do we make sense of the complex speech process in terms of its functional role of speech communication? How do we quantify the special role of speech timing? How do the dynamics relate to the variability of speech that has often been said to seriously hamper automatic speech recognition? How do we put the dynamic process of speech into a quantitative form to enable detailed analyses? And finally, how can we incorporate the knowledge of speech dynamics into computerized speech analysis and recognition algorithms? The answers to all these questions require building and applying computational models for the dynamic speech process.
What people are saying - Write a review
We haven't found any reviews in the usual places.
12 WHAT ARE MODELS OF SPEECH DYNAMICS?
13 WHY MODELING SPEECH DYNAMICS?
14 OUTLINE OF THE BOOK
A General Modeling and Computational Framework
22 MODEL DESIGN PHILOSOPHY AND OVERVIEW
23 MODEL COMPONENTS AND THE COMPUTATIONAL FRAMEWORK
232 Segmental Target Model
416 Decoding of Discrete States by Dynamic Programming
42 EXTENSION OF THE BASIC MODEL
422 Extension from Linear to Nonlinear Mapping
423 An Analytical Form of the Nonlinear Mapping Function
424 EStep for Parameter Estimation
425 MStep for Parameter Estimation
426 Decoding of Discrete States by Dynamic Programming
432 Experimental Results
233 Articulatory Dynamic Model
234 Functional Nonlinear Model for ArticulatorytoAcoustic Mapping
235 Weekly Nonlinear Model for Acoustic Distortion
236 Piecewise Linearized Approximation for ArticulatorytoAcoustic Mapping
Modeling From Acoustic Dynamics to Hidden Dynamics
32 STATISTICAL MODELS FOR ACOUSTIC SPEECH DYNAMICS
321 NonstationaryState HMMs
322 Multiregion Recursive Models
33 STATISTICAL MODELS FOR HIDDEN SPEECH DYNAMICS
331 Multiregion Nonlinear Dynamic System Models
332 Hidden Trajectory Models
Models with DiscreteValued Hidden Speech Dynamics
411 Probabilistic Formulation of the Basic Model
414 A Generalized ForwardBackward Algorithm
Models with ContinuousValued Hidden Speech Trajectories
511 Generating Stochastic Hidden Vocal Tract Resonance Trajectories
512 Generating Acoustic Observation Data
514 Computing Acoustic Likelihood
52 UNDERSTANDING MODEL BEHAVIOR BY COMPUTER SIMULATION
522 Effects of Speaking Rate on Reduction
523 Comparisons with Formant Measurement Data
524 Model Prediction of Vocal Tract Resonance Trajectories for Real Speech Utterances
525 Simulation Results on Model Prediction for Cepstral Trajectories
53 PARAMETER ESTIMATION
532 Vocal Tract Resonance Targets Distributional Parameters
54 APPLICATION TO PHONETIC RECOGNITION
542 Experimental Results
Other editions - View all
acoustic dynamic models acoustic feature acoustic observation approximation articulation articulatory dynamic model articulatory target auditory automatic speech recognition bandwidth basic model cepstral cepstrum chapter coarticulation computational framework constraints covariance matrix deﬁned described difﬁcult dynamic Bayesian network dynamic speech modeling E-step EM algorithm f1 and f2 ﬁlter ﬁrst-order ﬁxed formant frame Gaussian hidden dynamic models hidden dynamic variables hidden trajectory human speech implementation it+l iterations iy aa iy linear cepstra linguistic Markov chain mean vector model of speech model parameters multitiered nonlinear function observation equation optimization output parameter estimation parameter learning phonetic reduction phonological model phonological units piecewise linear quantization random recursion represented residual resonance frequency rs)Ts segmental HMM sequence simpliﬁed speaking rate speciﬁc speech acoustics speech chain speech dynamics speech process speech recognition Taylor series temporal time-varying TIMIT trajectory model values vocal tract Vocal Tract Resonance VTR frequency VTR tracking xt[i
Page xi - Acknowledgments THIS BOOK WOULD NOT HAVE BEEN POSSIBLE WITHOUT the help and prayers of many people.
Page 103 - L. Deng, L. Lee, H. Attias, and A. Acero. "A structured speech model with continuous hidden dynamics and predictionresidual training for tracking vocal tract resonances,
Page 97 - H. BOURLARD, H. HERMANSKY, AND N. MORGAN. "Towards increasing speech recognition error rates,
Page 97 - No. (#115-9732388), and was carried out at the 1998 Workshop on Language Engineering, Center for Language and Speech Processing, Johns Hopkins University.
Page 103 - Pitermann, Michel. 2000. Effect of speaking rate and contrastive stress on formant dynamics and vowel perception.