EEweb Home     ::     Graduate Courses     ::     Undergraduate Courses     ::     My Home

Course Description Form

Course number and title: EEM214A Digital Speech Processing
Credits: 4
Instructor(s)-in-charge: Abeer Alwan (alwan@ee.ucla.edu)
Course type: Lecture
Required or Elective: A Signals and Systems course.
Course Schedule:
Lecture: 3 hrs/week.
Lab: 2 hrs/week.
Outside Study: 7 hrs/week.
 
Course Assessment:
Homework: 6 assignments.
Project Reports: 1 project.
Exams: 1 midterm and 1 final examination.
 
Grading Policy: Typically, 20% HW, 20% project, 25% midterm, and 35% final.
Course Prerequisites: EE113
Catalog Description: Theory and applications of digital processing of speech signals. Mathematical models of human speech production and perception mechanisms, speech analysis/synthesis. Techniques include linear prediction, filter-bank models, and homomorphic filtering. Applications to speech synthesis, automatic recognition, and hearing aids.  
Textbook and any related course material:
Digital Speech Processing but Rabiner and Schafer, 2010
 
Course Website
Topics covered in the course:
LTI and Digital Signal Processing Review.
The Basic Units of Speech. Text-to-Speech Synthesis Techniques.
The Short Time Fourier Transform.
Vocoders and Spectrograms.
Linear-Predictive Coding (LPC). LPC estimate order and its Frequency-domain interpretation .
The Levinson Durbin Recursion.
Acoustic Tube Models
Homomorphic Analysis.
Introduction to Speech Coding.
Introduction to Automatic Speech Recognition
Will this course involve computer assignments? YES Will this course have TA(s) when it is offered? NO

:: Last modified: February 2013 by J. Lin ::

Copyright © 2003 UCLA Electrical and Computer Engineering Department. All rights reserved.
Please contact eeweb@ee.ucla.edu for comments or questions for the website.