CPSC 689-604: Special topics in Speech and Face Recognition

Spring 2007

Instructor: Ricardo Gutierrez-Osuna
Office: 520A HRBB
Phone: 979.845.2942
Email: rgutier[at]cs.tamu.edu

Course Description: The objective of this course is to familiarize students with the fundamentals of speech and face recognition through selected readings from the literature. The contents of the course are broad and cross-disciplinary, and will include:

Course organization: The course will be organized as a seminar, in which students prepare written critiques and oral presentations of selected papers, and also work in a semester-long open-ended project. Grading will be weighted as follows:

Required background: Students are expected to have background in signals and systems, linear algebra, and probability theory. Knowledge of signal processing and pattern recognition is helpful but not required. Please contact Dr. Gutierrez if you are interested in the course but are unsure you meet these requirements.

Reading and presentation schedule (Tentative)

Date
Paper title Presenter
01/16
Classes suspended due to weather  
01/18
Course introduction Ricardo Gutierrez
Speech recognition
01/23
Vocal tract acoustics
Daniel Felps
01/25
The motor theory of speech perception revisited Neal Audenaert
01/30
The TRACE model of speech perception Brian Davis
02/01
Recognizing spoken words: The neighborhood activation model Yinan Fan
02/06
Speech analysis and synthesis by linear prediction of the speech wave Tuneesh Lella
02/08
Should recognizers have ears? Pedro Davalos
02/13
Signal modeling techniques in speech recognition (draft) Hassan Kingravi
02/15
Speech Recognition: Statistical Methods (HMM1) (HMM2) Pankaj Rajan
02/20
Rapid speaker adaptation in eigenvoice space Henry Choi
02/22
How should a speech recognizer work? Neal Audenaert
Speaker recognition
02/27
Multidimensional representation of personal quality of vowels and its acoustical correlates
Pedro Davalos
03/01
Learning to recognize talkers from natural, sinewave, and reversed speech samples Pankaj Rajan
03/06
A tutorial on text-independent speaker verification Hassan Kingravi
03/08
Speaker transformation algorithm using segmental codebooks (STASC) Brian Davis
03/13
Spring break  
03/15
Spring break  
Face recognition
03/20
Face recognition by humans: nineteen results all computer vision researchers should know about Daniel Felps
03/22
From pixels to people: a model of familiar face recognition Tuneesh Lella
03/27
A unified account of the effects of distinctiveness, inversion and race in face recognition Henry Choi
03/29
The use of facial motion and facial form during the processing of identity Yinan Fan
04/03
Human facial illustrations: creation and psychophysical evaluation Pankaj Rajan
04/05
Detecting faces in images: a survey Neal Audenaert
04/10
Eigenfaces for Recognition Pedro Davalos
04/12
Face recognition using Laplacianfaces Hassan Kingravi
04/17
Face recognition based on fitting a 3D morphable model Brian Davis
04/19
Classifying facial actions Henry Choi
Audio-visual integration
04/24
Audio-visual integration in multimodal communication Tuneesh Lella
04/26
Trainable videorealistic speech animation Yinan Fan
05/01
No class (Redefined day)  
05/03
No class (Reading day)  
05/09
Final presentations (8:00 - 10:00 AM)