PROGRAM

Tues., June 21: Pre-Conference Seminars


Morning Session, Parallel Seminars - 10:00-13:00

10:00-13:00 - Fundamentals of Phase, Group Delay and Cepstral Analysis
                            Prof. Al Oppenheim of MIT

10:00-13:00 - Speech Transcription Overview – Markets, Applications &
                     Technologies

                            Dr. Sara Basson of IBM and Prof. Ami Moyal of Afeka


Lunch Break - 13:00-15:00

Afternoon Session, Parallel Seminars - 15:00-18:00

15:00-18:00 - Fundamentals of Hidden Markov Models and their Application to
                     Speech Recognition Technology

                            Prof. Lawrence Rabiner of Rutgers University and
                     UC Santa Barbara

15:00-18:00 - Multimodal Human-Machine Interaction
                            Dr. Matthew Yuschik of Multimodal interfaces, LLC


Wed., June 22: SPEECH PROCESSING CONFERENCE

Opening Session – 8:30-9:30

8:30-9:00 Networking and Registration
9:00-9:30 Welcoming Remarks

- Prof.  Ami  Moyal – Conference Chairman
- Dr. Nava Shaked – AVIOS Israel Chairman
- Mr. Eden Bar Tal - General Manager, Ministry of Communication

Keynote Speaker – 9:30-10:30

9:30-10:30 Scaling Up Speech Technology
                 Dr. Michael Cohen, Google, USA

Coffee Break - 10:30-11:00

Parallel Sessions I & II – 11:00-12:00

Session I: Speech Recognition
Session Chair: Prof. Larry Rabiner

11:00-11:15 The Power of Fusing Speech Recognition & Voice Biometrics
                         Technologies
                   Almog Aley-Raz - Nuance Communications

11:15-11:30 Acoustic Spatiotemporal Modeling using Deep Machine
                         Learning for Robust Phoneme Recognition

                   Itamar Arel - The University of Tennessee, USA
                   Shay Berant and Tsvi Slonim - Binatix, Inc., USA
                   Ami Moyal - Afeka Academic College of Engineering

11:30-11:45 Robust Speech Recognition using an Auxiliary Laser-Diode
                   Yekutiel Avargel, Tal Bakish, Gabi Horovitz, Yechiel Kurtz -
                   Audiozoom

11:45-12:00 Natural Speech Interface in Domain-Specific Dialogue
                   Dikla Shechnik, Noam Lotner, Michal Gishri, Ami Moyal,
                   Vered Aharonson – Afeka Academic College of Engineering

Session II: Human-Machine Interaction
Session Chair: Dr. Nava Shaked

11:00-11:15 Hands Free Technical Manual
                   Dina Goren-Bar – Afeka Academic College of Engineering and
                   Optimum Group
                   Tal Sasson - Afeka Academic College of Engineering

11:15-11:30 Multimodal Interfaces for Micro User Actions
                   Eran Aharonson - Intuitive User Interfaces
                   Vered Aharonson - Afeka Academic College of Engineering

11:30-11:45 Horror as never before! The First Interactive Cine Film
                   Detlev Artelt - Aixvox, Germany
                   Nava Shaked - Brit Business Technologies

11:45-12:00 Identify Cultural Aspects in Use of In-vehicle Speech
                         Applications

                   Ute Winter, Omer Tsimhoni - General Motors,
                   Advanced Technical Center Israel

Parallel Sessions III & IV – 12:00-13:00

Session III: Speaker Diarization and Verification
Session Chair: Dr. Matthew Yuschik

12:00-12:15 Speaker Diarization using Unsupervised Compensation of
                         Within-Speaker Variability
                   Hagai Aronowitz - IBM Research

12:15-12:30 Unsupervised Speaker Separation for Contact Center
                         Interactions

                   Tzach Ashkenazi, Shimrit Artzi, Ronen Lapardon, 
                   Merav Ben-Asher, Gil Dobry, Moshe Wasserblat, Oren Pereg -                   NICE

12:30-12:45 Detecting Goats in Speaker Verification Systems
                   Orith Toledo-Ronen, Hagai Aronowitz - IBM

12:45-13:00 Future Challenges in Speaker Diarization
                   Itshak Lapidot - Sami Shamoon College
                   Hugo Guterman – Ben Gurion University

Session IV Applications     
Session Chair: Dr. Sara Basson

12:00-12:15 Real-Time Analytics
                   Moshe Wasserblat, Oren Pereg, Tzach Ashkenazi, Shimrit Artzi,
                   Ronen Lapardon, Merav Ben-Asher – NICE

12:15-12:30 TTS Application: Earth surface as an Info-Sphere for Traveler
                   Alexei Cherenkov - Toozla, Russia

12:30-12:45 Implementation of Speech Recognition Technology in
                         Smart-Home Applications

                   Zohar Dvir – Zohar Dvir Yazamut

12:45-13:00 Building a Dynamic Corpus for Hebrew: Observations,
                         Challenges & Solutions

                   Ron Hasson – Aharon Speech Technologies

Lunch Break - 13:00-14:30

Session V – 14:30-15:20

Session V: Speech Processing in the Security Market
Session Chair: Prof. Ami Moyal

14:30-14:55 Safe Rise – Challenging the Ability to Fusion
                   Shahar Belkin - FST21
                  

14:55-15:20 The Requirements of an Intelligence Organization from
                         Speech Processing Technologies
                   Shabtai Shavit – Athena
                   Former Director General of the Israeli Mossad


Coffee Break - 15:20-15:40

Parallel Sessions VI & VII - 15:40-16:40

Session VI: Speaker Traits
Session Chair: Dr. Vered Aharonson

15:40-15:55 Database and Instance Selection for Speech Emotion
                         Recognition: Is More More?
                   Björn Schuller, Zixing Zhang, and Gerhard Rigoll -
                   Institute for Human-Machine Communication, Germany

15:55-16:10 Speaker Normalization in Detecting Angry Speech
                   Noam Amir - Department of Communication Disorders,
                   Sackler Faculty of Medicine, Tel-Aviv University

16:10-16:25 Age Group Classification Based on Introduction Sentences
                   Ron M. Hecht, Aharon Bar Hillel, Dan Levi, Ute Winter,
                   Ran Y. Gazit, Omer Tsimhoni -
                   General Motors, Advanced Technical Center Israel

16:25-16:40 Cepstral and Wavelets Methods for Pitch Tracking in Speech 
                         Processing of Tonal Languages
                   Victor Katsnelson, Eduard Polityko - Speech Modules

Session VII: Feature Extraction
Session Chair: Prof. Al Oppenheim

15:40-15:55 Non – Stationary Analysis of Speech applied to 
                         Perceptual Linear Prediction
                   Oron Gamliel - Department of Electrical and Computer 
                   Engineering, Ben Gurion University
                   Ilan D. Shallom - NSC Natural Speech Communication

15:55-16:10 Glottal Inverse Filtering: a New Road-Map and First Results
                   Sandra Dias, Ricardo Sousa, Aníbal Ferreira - University of Porto,
                   School of Engineering, Portugal

16:10-16:25 Advances in Spectral Parameterization for Statistical
                         (HMM-Based) TTS
                   Slava Shechtman, Alexander Sorin - IBM

16:25-16:40 On Feature Extraction for Voice Pathology Detection from
                         Speech Signals
                   Aharon Satt, Zvi Kons, Ron Hoory – IBM, Haifa Research Lab

Closing Remarks – 16:40-17:00