| |
| |
Preface | |
| |
| |
Signal Processing Background | |
| |
| |
Propaedeutic | |
| |
| |
Review of DSP Concepts and Notation | |
| |
| |
Review of Probability and Stochastic Processes | |
| |
| |
Topics in Statistical Pattern Recognition | |
| |
| |
Information and Entropy | |
| |
| |
Phasors and Steady-State Solutions | |
| |
| |
Onward to Speech Processing | |
| |
| |
Speech Production and Modeling | |
| |
| |
Fundamentals of Speech Science | |
| |
| |
Speech Communication | |
| |
| |
Anatomy and Physiology of the Speech Production System | |
| |
| |
Phonemics and Phonetics | |
| |
| |
Modeling Speech Production | |
| |
| |
Acoustic Theory of Speech Production | |
| |
| |
Discrete-Time Modeling | |
| |
| |
Analysis Techniques | |
| |
| |
Short-Term Processing of Speech | |
| |
| |
Short-Term Measures from Long-Term Concepts | |
| |
| |
Example Short-Term Features and Applications | |
| |
| |
Linear Prediction Analysis | |
| |
| |
Long-Term LP Analysis by System Identification | |
| |
| |
How Good Is the LP Model? | |
| |
| |
Short-Term LP Analysis | |
| |
| |
Alternative Representations of the LP Coefficients | |
| |
| |
Applications of LP in Speech Analysis | |
| |
| |
Cepstral Analysis | |
| |
| |
"Real" Cepstrum | |
| |
| |
Complex Cepstrum | |
| |
| |
A Critical Analysis of the Cepstrum and Conclusions | |
| |
| |
Coding, Enhancement and Quality Assessment | |
| |
| |
Speech Coding and Synthesis | |
| |
| |
Optimum Scalar and Vector Quantization | |
| |
| |
Waveform Coding | |
| |
| |
Vocoders | |
| |
| |
Measuring the Quality of Speech Compression | |
| |
| |
Speech Enhancement | |
| |
| |
Classification of Speech Enhancement Methods | |
| |
| |
Short-Term Spectral Amplitude Techniques | |
| |
| |
Speech Modeling and Wiener Filtering | |
| |
| |
Adaptive Noise Canceling | |
| |
| |
Systems Based on Fundamental Frequency Tracking | |
| |
| |
Performance Evaluation | |
| |
| |
Speech Quality Assessment | |
| |
| |
Subjective Quality Measures | |
| |
| |
Objective Quality Measures | |
| |
| |
Objective Versus Subjective Measures | |
| |
| |
Recognition | |
| |
| |
The Speech Recognition Problem | |
| |
| |
The "Dimensions of Difficulty" | |
| |
| |
Related Problems and Approaches | |
| |
| |
Dynamic Time Warping | |
| |
| |
Dynamic Programming | |
| |
| |
Dynamic Time Warping Applied to IWR | |
| |
| |
DTW Applied to CSR | |
| |
| |
Training Issues in DTW Algorithms | |
| |
| |
The Hidden Markov Model | |
| |
| |
Theoretical Developments | |
| |
| |
Practical Issues | |
| |
| |
First View of Recognition Systems Based on HMMs | |
| |
| |
Language Modeling | |
| |
| |
Formal Tools for Linguistic Processing | |
| |
| |
HMMs, Finite State Automata, and Regular Grammars | |
| |
| |
A "Bottom-Up" Parsing Example | |
| |
| |
Principles of "Top-Down" Recognizers | |
| |
| |
Other Language Models | |
| |
| |
IWR As "CSR" | |
| |
| |
Standard Databases for Speech-Recognition Research | |
| |
| |
A Survey of Language-Model-Based Systems | |
| |
| |
The Artificial Neural Network | |
| |
| |
The Artificial Neuron | |
| |
| |
Network Principles and Paradigms | |
| |
| |
Applications of ANNs in Speech Recognition | |
| |
| |
Index | |