EE6307 - Speech Systems

Course Description:  

Speech Systems offers a theoretical and practical understanding of how human speech can be processed by computers. This course is designed to understand the application of statistical and machine learning techniques to speech data. It covers speech recognition, speaker recognition, speech synthesis, and keyword spotting systems. The course involves practicals where the student builds working speech systems using existing toolkits. Details of the state-of-the-art algorithms and their limitations will also be discussed. 

Prerequisites: 

Basic Calculus, Probability and Random Processes, Linear Algebra, Digital Signal Processing and Machine Learning

Course contents: 

• Acoustic Theory of Feature Extraction: Acoustic theory of speech production and speech signal processing

• Automatic Speech Recognition: Template matching approaches, hidden Markov models, deep acoustic modeling, language modeling

• Speaker Recognition: Gaussian mixture modeling, universal background models, minimum divergence criteria, probabilistic LDA, system building

• Speech Synthesis: Text analysis, Pronunciation, prosody, waveform generation using unit selection, HTS and wavenets, voice building and modification.

References:

1. Huang, Acero and Hon, Spoken Language Processing: A Guide to Theory, Algorithm and System Development, Prentice Hall

2. Rabiner and Schafer, Theory and Applications of Digital Speech Processing,  Prentice Hall

3. CM Bishop, Pattern Recognition and Machine Learning,  Springer

Slides

1. Speech Systems - Introduction

2. Acoustic Theory of Speech Production and Feature Extraction

3. Speaker Recognition System

4. Statistical Acoustic Modeling

5. Neural Acoustic Modeling

6. Project Topics