1. Course Description
<br>
<br>This course introduces signal processing techniques for processing speech 
<br>signals. Course content will be split into three major parts: speech signal 
<br>processing techniques and analysis methods, automatic speech recognition systems, 
<br>and current research trends in speech and language processing. Evaluation is done 
<br>based on two major components: traditional evaluation (homework + midterm) & 
<br>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 Applications of Digital Speech Processing, 
<br>Prentice Hall, 2010
<br>Huang, Acero, and Hon: Spoken Language Procesing, Prentice Hall, 2001
<br>T. Quatieri: Discrete-time Speech Signal Processing, Prentice Hall, 2001
<br>
<br>4. Teaching Methods
<br>
<br>English teaching. Mix of lectures and discussions
<br>
<br>5. Syllabus
<br>
<br>Overview: Course overview, Review of basic DSP
<br>Overview:  Introduction to Speech Production & Acoustics Speech Models 
<br>Speech Analysis: Short-term Time Domain Processing, Short-time Fourier Transform
<br>Speech Analysis: All-pole model: Linear Prediction
<br>Speech Analysis: Homomorphic Signal 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 Adaptation
<br>ASR: Advanced issues in ASR
<br>Exemplary Speech Technology (I): Voice Activity Detector & Diarization System
<br>Exemplary Speech Technology (II): Speaker and Language Identity Recognition
<br>Behavior Informatics from Speech and Language: Affective Computing
<br>Behavior Informatics from Speech and Language: Mental Health Applications
<br>
<br>6. Evaluation
<br>
<br>Homework 15% (each 5%)
<br>Midterm 25%
<br>Project  60% (1st presentation 15%, final presentation 25%, participation 10%, 
<br>report 10%)
<br>No late homework accepted
<br>
<br>7. Course Website
<br>
<br>(UNDER CONSTRUCTION)