Afeka Conference for Speech Processing
|
|
08:30 - 09:15
|
Networking & Registration
|
|
09:15 - 09:30
|
Welcome Remarks
- Prof. Ami Moyal, President, Afeka
- Dr. Irit Opher, Conference Chairman, ACLP, Afeka
|
|
09:30 - 10:30
|
Keynote
|
|
10:30 - 11:00
|
--- Coffee Break ---
|
|
11:00 - 12:40 |
First Session
- Special Talk - Sound Capture and Speech Enhancement for the Needs of Distant Speech Recognition
Dr. Ivan J. Tashev, Microsoft Research Labs, Redmond
- Recursive and Distributed Expectation-Maximization (EM) Algorithms for Speaker Localization and Tracking
Prof. Sharon Gannot, Faculty of Engineering, Bar-Ilan University
- The Advantages of Semantic LM over Statistical LM
Mr. Noam Ziv, CEO, Semantic Interfaces Ltd
- Automatic Transcription of High-School Lessons in Hebrew for Hearing Impaired Students
Mr. Yarden Karny, ACLP, Afeka
|
|
12:40 - 14:15 |
--- Lunch ---
|
|
14:15 - 15:15 |
Keynote
|
|
15:15 - 16:15 |
Second Session
- Industry Perspective - Conversational Speech: From Voice Connectivity to Voice.AI
Mr. Gidi Adlersberg, Product Marketing Manager, AudioCodes
Presentation
-
Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation
Ms. Inbar Mosseri, Google Research
|
|
16:15 - 16:30
|
--- Coffee Break --- |
Satellite Event - Unsupervised Machine Learning Seminar
|
|
16:30 - 16:45
|
Welcome Remarks
- Dr. Itshak Lapidot, Seminar Chairman, ACLP, Afeka
|
| 16:45 - 17:45 |
Keynote
|
| 17:45 - 18:45 |
Short Lectures
- Incremental Speaker Segments Clustering
Dr. Itshak Lapidot, ACLP, Afeka
- Learning to Estimate Under Transformed Probability Measures.
Dr. Koby Todros, Dept. of ECE, Ben-Gurion-University of the Negev
- An Anatomy of Scaling Unsupervised Learning for Online Gaming.
- Mr. Igal Grinis, Head of Research , Tomobox
Presentation
Video
|