Course Details

Subject {L-T-P / C} : EE4501 : Speech Processing {3-0-0 / 3}
Subject Nature : Theory
Coordinator : Prof. Prasanna Kumar Sahu

Syllabus

Introduction, Historical Background, Synthetic Audio, Speech Analysis and Synthesis Overview, Brief History of Automatic Speech Recognition, Mathematical Background, Digital Signal Processing, Pattern Classification, Acoustics, Wave Basics, Acoustic Tube Modeling of Speech Production, Auditory Perception, Psychoacoustics, Speech Perception, Human Speech Recognition, Speech Features, The Auditory System as a Filter Bank, The Cepstrum as a Spectral Analyzer, Linear Prediction, Automatic Speech Recognition, Feature Extraction for ASR, Deterministic Sequence Recognition for ASR, Statistical Sequence Recognition, Some aspects of Computer Music Synthesis, Music Signal Analysis, Music Retrieval, Speaker Verification

Course Objectives

  1. The purpose of this course is to explain how DSP techniques could be used for solving problems in speech communication

Course Outcomes

Illustrate how the speech production is modeled
Summarize the various techniques involved in collecting the features from the speech signal in both time and frequency domain
Compare the various techniques involved in speech and speaker detection
Summarize the various speech compression techniques

Essential Reading

  1. S.D Apte, Speech and Audio Processing, Wiley India Edition , 2015
  2. Rabiner Lawrence R., and Biing-Hwang Juang, Fundamentals of Speech Recognition, Prentice Hall International , 1998

Supplementary Reading

  1. Gold Ben, Nelson Morgan, and Dan Ellis, Speech and Audio signal processing: processing and perception of speech and music, John Wiley & Sons , 2011
  2. Benesty Jacob, M. Mohan Sondhi, and Yiteng Huang, Handbook of speech processing, Springer , 2007