Friday Oct. 31
Opening session 5:00 – 7:00
WELCOME
5:00-5:30 Gathering and refreshments
5:30-5:40 Pierre Divenyi
Chair’s introduction
INTRODUCTORY LECTURE
5:40-6:20 Chris Darwin
Speech segregation: problems
and perspectives
DISCUSSION: WHAT ASA EXPECTS COMPUTATIONAL SEPARATION TO ACHIEVE
6:20-6:50 Al Bregman (moderator)
6:50-8:00 Reception
Saturday November 1
Morning session 8:00 – 12:30
SETTING THE SCENE
Chair: Dan Ellis
8:00-8:40 Nat Durlach
Separation, localization,
and comprehension of multiple, simultaneous speech signals by humans,
machines, and human-machine systems
8:40-9:20 Tom Huang
Interplay between audio
and visual scene analysis
9:20-10:00 Elyse Sussman
Auditory scene analysis:
Examining the role of nonlinguistic auditory processing in speech perception
10:00-10:30 Break
10:30-11:10 Rich Stern
Speech separation in recognition
11:10-11:50 Sam Roweis
Factorial Models and Refiltering
for Speech Separation and Denoising
DISCUSSION: INTERPLAY OF MULTIPLE PERSPECTIVES
11:50-12:30 Martin Cooke and Dan Ellis (moderators)
12:30-1:30 Lunch
Afternoon session 1:30 – 6:00
AUDITORY SCENE ANALYSIS: NEURAL AND COMPUTATIONAL
Chair: Guy Brown
1:30-2:10 Claude Alain
Neural concomitant of vowel
segregation
2:10-2:50 Peter Cariani
Recurrent timing nets for
F0-based sound separation
2:50-3:30 Alain de Cheveigné
The cancellation principle
in auditory scene analysis
3:30-4:00 Break
4:00-4:40 Malcolm Slaney
Wither CASA?
4:40-5:20 DeLiang Wang
On computational objectives
of auditory scene analysis
DISCUSSION: OPEN PROBLEMS IN SPEECH SEPARATION
5:20-6:00 DeLiang Wang and Te-Won Lee (moderators)
Morning session 8:00-12:30
FOCUS ON SPEECH AND
PERCEPTION
Chair: DeLiang Wang
8:00-8:40 Bhiksha Raj
Maximum-likelihood multi-channel speaker separation using factorial
HMMs
8:40-9:20 Hideki Kawahara and Toshio Irino
Underlying principles
of a high-quality speech manipulation system STRAIGHT and its application
to speech segregation
9:20-10:00 Guy Brown
Auditory models for speech processing in noisy and reverberant conditions
10:00-10:30 Break
10:30-11:10 Douglas Brungart
Informational and energetic
masking effects in multitalker speech perception
11:10-11:50 Pierre Divenyi
Masking feature information
in multi-stream speech-analogue displays
DISCUSSION: USING INFORMATION IN SPEECH SEPARATION
11:50-12:30 Rich Stern and Nat Durlach (moderators)
12:30-1:30 Lunch
MACHINE LEARNING AND
OTHER TECHNIQUES
Chair: Sam Roweis
1:30-2:10 Dan Ellis
Sound, mixtures, and learning
2:10-2:50 Te-Won Lee
Speech signal understanding
using graphical models
2:50-3:30 Paris Smaragdis
Exploiting redundancy
to construct listening systems
3:30-4:00 Break
4:00-4:40 Martin Cooke
Glimpsing speech
DISCUSSION: PRESENT AND FUTURE OF SPEECH SEPARATION
4:40-5:30 Pierre
Divenyi, Dan Ellis, DeLiang Wang (moderators)
[top of page]