 |
Seminar's Agenda (pdf 38KB)
9:30 Arrival
9:45 Welcome
Zohar Sivan, Mgr. Telecom and Media Systems,
IBM Haifa Research Labs
Session 1: Speech Recognition and Synthesis
10:00 Embedded Speech Recognition for Mass-market
Wireless Devices, Eran Aharonson, CEO, ART
Advanced Recognition Technologies Inc.
(Abstract)
10:30 Concatenative Text-to-speech for the
Embedded Environment, Ron Hoory, Haifa Research Labs
(Abstract , Presentation)
10:55 Distributed Speech Recognition - Standardization
Activity, Alex Sorin, Haifa Research Labs
(Abstract , Presentation)
11:20 - 11:35 Break
11:35 Challenges in Speaker-independent Name
Dialing for Cellphones, Adoram Erell, Intel
(Abstract , Presentation)
Session 2: Speaker Recognition
12:00 Speaker Verification with Optimal
Feature Space, Arnon Cohen, Ben-Gurion University
(Abstract , Presentation)
|
|
|
|
12:25 Speaker Verification by Adapted Phoneme
Gaussian Mixture Models, Yuval Bistritz, Tel-Aviv University
(Abstract , Presentation)
12:50 Speaker Detection in Multi-speaker Sessions,
Ran Gazit, Chief Scientist, Persay Ltd.
(Abstract)
13:15 - 14:30 Lunch
14:30 Remarks,
Michael Rodeh, Director, IBM Haifa Labs
Keynote
14:45 State of the Art Large Vocabulary Speech Recognition:
The MALACH Project, Michael Picheny,
IBM T.J. Watson Research Center
(Abstract)
15:45 - 16:00 Coffee Break
Session 3: Speech Coding and Enhancement
16:00 Speech Coding at Very Low Bit Rates,
David Malah ¹, Technion
(Abstract , Presentation)
16:25 Speech Enhancement Based on the General
Transfer Function GSC and Postfiltering, Sharon Gannot
and Israel Cohen, Technion
(Abstract , Presentation)
16:50 Autodirective Dual Microphone and
Other Alango DSP Technologies,
Alexander Goldin, CEO, Alango Ltd.
(Abstract , Presentation)
|
|
