About the Book

Speech and Audio Processing is a text targeted towards the final year undergraduate Speech Processing course and PG students in ECE, CS, and IT streams.
This book aims at explaining the basic concepts in a clear-cut and simplified manner. It begins with the human speech production mechanism and then goes on to the fundamental parameters of speech such as pitch frequency, formants, spectral features like log spectrum, 3-D spectrogram, cepstral features, MFCC, linear prediction coefficients, transform-domain parameters, template matching techniques, etc.
It deals with applications like speech coding, speech recognition, speaker recognition, and speech synthesis. It also includes the techniques used for musical signal synthesis and musical instrument recognition in polyphonic music.
The book uses plenty of MATLAB programs along with their outputs, and provides a graphical interpretation of the results.

About the Author

Dr. Shaila Dinkar Apte is currently working as a Professor at Rajarshi Shahu College of Engineering, Pune. She has formerly been an Assistant Professor in Walchand College of Engineering, Sangli, for 27 years; a member of the Board of Studies at Shivaji University and a Principal Investigator for a research project sponsored by the Armament Research and Development Establishment (ARDE), New Delhi. She has a vast teaching experience of 28 years in Electronics Engineering, and enjoys great popularity amongst students. She has been teaching Digital Signal Processing for the last 18 years. Dr. Shaila Dinkar Apte completed her M.Sc. in Electronics from Mumbai University in 1976 with the first rank. She then received her M.E. in Electronics in 1991 and Ph.D. in 2001 in Electronics Engineering from Walchand College of Engineering, Sangli (under Shivaji University, Kolhapur). Her Ph.D. thesis involved work on speaker modeling using an optimal mother wavelet. She has published 22 papers in reputed international journals, more than 40 papers in international conferences and about 15 papers in national conferences. She has a patent published to her credit related to the generation of the mother wavelet from a speech signal. She has published a book titled ‘Digital Signal Processing’ with Wiley India. A second reprint of second edition of this title is now in the market. She is also a reviewer for the International Journal of Speech Technology (Springer) and the International Journal of Digital Signal Processing (Elsevier). She is currently guiding 5 Ph.D. candidates in Speech Processing and other related areas. Three candidates have completed their Ph.D. thesis under her guidance About 35 candidates have completed their M.E. dissertations - almost all of them in the area of Speech Processing - under her guidance.

Table of Contents:
Fundamentals of Speech Learning Objectives · The Human Speech Production Mechanism · LTI Model for Speech Production · Nature of the Speech Signal · Linear Time-Varying Model · Phonetics · Types of Speech · Voiced and Unvoiced Decision Making · Audio File Formats: Nature of the WAV File Summary Key Terms Multiple Choice Questions Review Questions Problems Answers Parameters of Speech: Pitch and Formants Learning Objectives · Fundamental Frequency or Pitch Frequency · Parallel Processing Approach for Calculation of Pitch Frequency · Pitch Period Measurement Using Spectral Domain · Cepstral Domain · Formants and Their Relation With LPC · Evaluation of Formants Using Cepstrum · Evaluation of Formants Using Log Spectrum · Evaluation of Formants Using Power Spectral Density Estimate · Estimation of Formants: Other Methods Summary Key Terms Multiple Choice Questions Review Questions Problems Answers Spectral Parameters of Speech Learning Objectives · Homomorphic Processing · Cepstral Analysis of Speech: Cepstral Coefficients · The Auditory System as a Filter Bank · Mel Frequency Cepstral Coefficients (MFCCs) · Perceptual Linear Prediction (PLP) · Log Frequency Power Coefficients (LFPCs) · RelAtive SpecTrAl Perceptual Linear Prediction (Rasta-PLP): Strategies for Robustness · Short-Time Spectral Analysis of Speech: Short-Time Fourier Transform (STFT) · Wavelet Transform Analysis of Speech Summary Key Terms Multiple Choice Questions Review Questions Problems Answers Linear Prediction of Speech Learning Objectives · Lattice Structure Realization · Forward Linear Prediction · Autocorrelation Method · Covariance Method · Lattice Methods · Selection of Order of the Predictor · Line Spectral Frequencies/Line Spectral Pair Frequencies Summary Key Terms Multiple Choice Questions Review Questions Problems Answers Speech Quantization and Coding Learning Objectives · Uniform and Non-Uniform Quantizers and Coder · Companded Quantizer · Uniform Quantization of Non-uniform Sources: Adaptive Quantizers · Waveform Coding of Speech · Comparison of Different Waveform Coding Techniques · Parametric Speech Coding Techniques · Sinusoidal Speech Coding Techniques · Mixed Excitation Linear Prediction Coder · Multi-Mode Speech Coding (Hybrid Coder) · Transform Domain Coding of Speech Summary Key Terms Multiple Choice Questions Review Questions Problems Answers Speech Processing Applications Learning Objectives · Speech Recognition Systems · Architecture of a Large Vocabulary Continuous Speech Recognition System · Deterministic Sequence Recognition for ASR · Statistical Sequence Recognition for ASR · Statistical Pattern Recognition and Parameter Estimation · VQ-HMM-Based Speech Recognition · Discriminant Acoustic Probability Estimation · Word Spotting/Keyword Spotting · Speech Recognition and Understanding · Speaker Recognition · Distortion Measures: Mathematical and Perceptual · Speech Enhancement · Adaptive Echo Cancellation Summary Key Terms Multiple Choice Questions Review Questions with Pointers Suggested Projects Answers Speech Synthesis Learning Objectives · A Text-to-Speech System · Synthesizer Technologies · Speech Synthesis Using Other Methods · Speech Transformations · Emotion Recognition from Speech · Watermarking for Authentication of a Speech/Music Signal Summary Key Terms Multiple Choice Questions Review Questions with Pointers Suggested Projects Answers Basics of Musical Instruments and Music Synthesis Learning Objectives · Indian Musical Instruments · Features Used for Classification · Music Synthesis · Musical Instrument Digital Interface (MIDI) · Streaming Audio · Piano Note Synthesis Using LPC and WT · Audio Standards Summary Key Terms Multiple Choice Questions Review Questions Problems (Write MATLAB Programs) Suggested Projects (Write MATLAB Programs) Answers Frequently Asked Short Questions With Answers Frequently Asked Long Questions With Pointers Bibliography Index