21EC735 Speech Signal Processing
Course Learning Objectives
● Introduce the models for speech production
● Develop Time domain and frequency domain speech processing techniques
● Introduce a predictive technique for speech compression
● Provide fundamental knowledge required to understand and analyze speech recognition, synthesis and speaker identification systems.
SYLLABUS COPY
MODULE - 1
Fundamentals of Human Speech Production
The Process of Speech Production, Short-Time Fourier representation of Speech, The Acoustic Theory of Speech production, Digital Models for Sampled Speech Signals.
MODULE - 2
Time-Domain Methods for Speech Processing
Introduction to Short-Time Analysis of Speech, Short-Time Energy and Short-Time Magnitude, Short-Time Zero-Crossing Rate, The Short-Time Autocorrelation Function, Speech vs Silence detection.
MODULE - 3
Frequency Domain Representations
Discrete-Time Fourier Analysis, Short-Time Fourier Analysis, Overlap Addition (OLA) and Filter Bank Summation (FBS) Method of Synthesis, Time-Decimated Filter Banks, Two-Channel Filter Banks, Modifications of the STFT.
MODULE - 4
The Cepstrum and Homomorphic Speech Processing
Introduction, Homomorphic Systems for Convolution, Homomorphic Analysis of the Speech Model, Computing the Short-Time Cepstrum and Complex Cepstrum of Speech, Homomorphic Filtering of Natural Speech, Cepstrum Analysis of All-Pole Models, Cepstrum Distance Measures.
MODULE - 5
Linear Predictive Analysis of Speech Signals
Introduction to Basic Principles of Linear Predictive Analysis, Computation of the Gain for the Model, Frequency Domain Interpretations of Linear Predictive Analysis, Solution of the LPC Equations, The Prediction Error Signal.
Course outcome
1. Model speech production system and describe the fundamentals of speech.
2. Apply time domain and frequency domain algorithms, on speech to find, enhance and modify speech parameters.
3. Choose an appropriate processing technique for a given application.
4. Analyse speech recognition, synthesis and speaker identification systems
Suggested Learning Resources
Text Books
1. Digital Processing of Speech Signals – L R Rabiner and R W Schafer, Pearson Education Asia, 2004. 2. Theory and Applications of Digital Speech Processing-Rabiner and Schafer, Pearson Education
2011.
Reference Books
1. Fundamentals of Speech Recognition- Lawrence Rabiner and Biing-Hwang Juang, Pearson Education, 2003.
2. Speech and Language Processing–An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition- Daniel Jurafsky and James H Martin, Pearson Prentice Hall, 2009.