Dynamic Speech Models (Synthesis Lectures on Speech and Audio Processing)

Dynamic Speech Models (Synthesis Lectures on Speech and Audio Processing)

ABSTRACT

Speech dynamics refer to the temporal characteristics in all stages of the human speech communication process. This speech ¡°chain¡± 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 are the compelling reasons for carrying out dynamic speech modeling? We provide the answer in two related aspects. First, scientific inquiry into the human speech code has been relentlessly pursued for several decades. As an essential carrier of human intelligence and knowledge, speech is the most natural form of human communication. Embedded in the speech code are linguistic (as well as para-linguistic) messages, which are conveyed through four levels of the speech chain. Underlying the robust encoding and transmission of the linguistic messages are the speech dynamics at all the four levels. Mathematical modeling of speech dynamics provides an effective tool in the scientific methods of studying the speech chain. Such scientific studies help understand why humans speak as they do and how humans exploit redundancy and variability by way of multitiered dynamic processes to enhance the efficiency and effectiveness of human speech communication. Second, advancement of human language technology, especially that in automatic recognition of natural-style human speech is also expected to benefit from comprehensive computational modeling of speech dynamics. The limitations of current speech recognition technology are serious and are well known. A commonly acknowledged and frequently discussed weakness of the statistical model underlying current speech recognition technology is the lack of adequate dynamic modeling schemes to provide correlation structure across the temporal speech observation sequence. Unfortunately, due to a variety of reasons, the majority of current research activities in this area favor only incremental modifications and improvements to the existing HMM-based state-of-the-art. For example, while the dynamic and correlation modeling is known to be an important topic, most of the systems nevertheless employ only an ultra-weak form of speech dynamics; e.g., differential or delta parameters. Strong-form dynamic speech modeling, which is the focus of this monograph, may serve as an ultimate solution to this problem.

After the introduction chapter, the main body of this monograph consists of four chapters. They cover various aspects of theory, algorithms, and applications of dynamic speech models, and provide a comprehensive survey of the research work in this area spanning over past 20 years. This monograph is intended as advanced materials of speech and signal processing for graudatelevel teaching, for professionals and engineering practioners, as well as for seasoned researchers and engineers specialized in speech processing.

KEYWORDS

Articulatory trajectories, Automatic speech recognition, Coarticulation, Discretizing hidden dynamics, Dynamic Bayesian network, Formant tracking, Generative modeling, Speech acoustics, Speech dynamics, Vocal tract resonance

CONTENTS

1. Introduction
1.1 What Are Speech Dynamics?
1.2 What Are Models of Speech Dynamics?
1.3 Why Modeling Speech Dynamics?
1.4 Outline of the Book

2. A General Modeling and Computational Framework
2.1 Background and Literature Review
2.2 Model Design Philosophy and Overview
2.3 Model Components and the Computational Framework
2.3.1 Overlapping Model for Multitiered Phonological Construct
2.3.2 Segmental Target Model
2.3.3 Articulatory Dynamic Model
2.3.4 Functional Nonlinear Model for Articulatory-to-Acoustic Mapping
2.3.5 Weakly Nonlinear Model for Acoustic Distortion
2.3.6 Piecewise Linearized Approximation for Articulatory-to-Acoustic Mapping
2.4 Summary

3. Modeling: From Acoustic Dynamics to Hidden Dynamics
3.1 Background and Introduction
3.2 Statistical Models for Acoustic Speech Dynamics
3.2.1 Nonstationary-State HMMs
3.2.2 Multiregion Recursive Models
3.3 Statistical Models for Hidden Speech Dynamics
3.3.1 Multiregion Nonlinear Dynamic System Models
3.3.2 Hidden Trajectory Models
3.4 Summary

4. Models with Discrete-Valued Hidden Speech Dynamics
4.1 Basic Model with Discretized Hidden Dynamics
4.1.1 Probabilistic Formulation of the Basic Model
4.1.2 Parameter Estimation for the Basic Model: Overview
4.1.3 EM Algorithm: The E-Step
4.1.4 A Generalized Forward-Backward Algorithm
4.1.5 EM Algorithm: The M-Step
4.1.6 Decoding of Discrete States by Dynamic Programming
4.2 Extension of the Basic Model
4.2.1 Extension from First-Order to Second-Order Dynamics
4.2.2 Extension from Linear to Nonlinear Mapping
4.2.3 An Analytical Form of the Nonlinear Mapping Function
4.2.4 E-Step for Parameter Estimation
4.2.5 M-Step for Parameter Estimation
4.2.6 Decoding of Discrete States by Dynamic Programming
4.3 Application to Automatic Tracking of Hidden Dynamics
4.3.1 Computation Efficiency: Exploiting Decomposability in the Observation Function
4.3.2 Experimental results
4.4 Summary

5. Models with Continuous-Valued Hidden Speech Trajectories
5.1 Overview of the Hidden Trajectory Model
5.1.1 Generating Stochastic Hidden Vocal Tract Resonance Trajectories
5.1.2 Generating Acoustic Observation Data
5.1.3 Linearizing Cepstral Prediction Function
5.1.4 Computing Acoustic Likelihood
5.2 Understanding Model Behavior by Computer Simulation
5.2.1 Effects of Stiffness Parameter on Reduction
5.2.2 Effects of Speaking Rate on Reduction
5.2.3 Comparisons with Formant Measurement Data
5.2.4 Model Prediction of Vocal Tract Resonance Trajectories for Real Speech Utterances
5.2.5 Simulation Results on Model Prediction for Cepstral Trajectories
5.3 Parameter Estimation
5.3.1 Cepstral Residuals¡¯ Distributional Parameters
5.3.2 Vocal Tract Resonance Targets¡¯ Distributional Parameters
5.4 Application to Phonetic Recognition
5.4.1 Experimental Design
5.4.2 Experimental Results
5.5 Summary

Password: ebooksclub.org
File size: 3.1 MB
Format: PDF

http://mihd.net/e2d68i

http://rapidshare.com/files/54413923/1598290649.rar