Speech and music are the most basic means of adult human communication. As technology advances and increasingly sophisticated tools become available to use with speech and music signals, scientists can study these sounds more effectively, and invent new ways of applying them for the benefit of humankind. This text includes coverage of the physiology and psychoacoustics of hearing as well as the results from research on pitch and speech perception, vocoding methods and information on many aspects of automatic speech recognition (ASR) systems. The authors have made use of their own research in these fields, as well as the methods and results of many other contributors.

Contents
Part I Historical Background

· Synthetic Audio: A Brief History

· Speech Analysis and Synthesis Overview

· Brief History of Automatic Speech Recognition

· Speech-Recognition Overview

Part II Mathematical Background

· Digital Signal Processing

· Digital Filters and Discrete Fourier Transform

· Pattern Classification

· Statistical Pattern Classification

Part III Acoustics

· Wave Basics

· Acoustic Tube Modeling of Speech Production

· Music Production

· Room Acoustics

Part IV Auditory Perception

· Ear Physiology

· Psychoacoustics

· Models of Pitch Perception

· Speech Perception

· Human Speech Recognition

Part V Speech Features

· The Auditory System as a Filter Bank

· The Cepstrum as a Spectral Analyzer

· Linear Prediction

Part VI Automatic Speech Recognition

· Feature Extraction for ASR

· Linguistic Categories for Speech Recognition

· Deterministic Sequence Recognition for ASR

· Statistical Sequence Recognition

· Statistical Model Training

· Discriminant Acoustic Probability Estimation

· Speech Recognition and Understanding

Part VII Synthesis And Coding

· Speech Synthesis

· Pitch Detection

· Vocoders

· Low-Rate Vocoders

· Medium-Rate and High-Rate Vocoders

Part VIII Other Applications

· Speech Transformations

· Some Aspects of Computer Music Synthesis

· Speaker Verification

Index