1. Course Desc<x>ription
<br>
<br>This course introduces signal processing 
<br>techniques for processing speech 
<br>signals. Course content will be split into 
<br>three major parts: speech signal 
<br>processing techniques and analysis 
<br>methods, automatic speech recognition 
<br>systems, and current research trends in 
<br>speech and language processing. 
<br>Evaluation is done ba<x>sed on two major 
<br>components: traditional evaluation 
<br>(homework + midterm) & project
<br>
<br>2. Required Textbooks
<br>
<br>Lecture notes and papers provided in class
<br>
<br>3. Reference Books
<br>
<br>Rabiner and Schafer: Theory and 
<br>Applications of Digital Speech Processing, 
<br>Prentice Hall, 2010
<br>Huang, Acero, and Hon: Spoken Language 
<br>Procesing, Prentice Hall, 2001
<br>T. Quatieri: Discrete-time Speech Signal 
<br>Processing, Prentice Hall, 2001
<br>
<br>4. Teaching Methods
<br>
<br>English teaching. Mix of lectures and 
<br>discussions
<br>
<br>5. Syllabus
<br>
<br>Overview: Course overview, Review of basic 
<br>DSP
<br>Overview:  Introduction to Speech 
<br>Production & Acoustics Speech Models 
<br>Speech Analysis: Short-term Time Domain 
<br>Processing, Short-time Fourier 
<br>Transform
<br>Speech Analysis: All-pole model: Linear 
<br>Prediction
<br>Speech Analysis: Homomorphic Signal 
<br>Processing & Cepstral Analysis
<br>ASR: Intro to Automatic Speech Recognition
<br>ASR: Hidden Markov Model  
<br>ASR: Language Model
<br>ASR: Robust front-end processing, Speaker 
<br>Adaptation
<br>ASR: Advanced issues in ASR
<br>
<br>
<br>
<br>6. Evaluation
<br>
<br>To be determined
<br>
<br>7. Course Website
<br>
<br>(UNDER CONSTRUCTION)