Weakly-supervised phrase assignment from text in a speech-synthesis system using noisy labels
- Asaf Rendel
- Raul Fernandez
- et al.
- 2017
- INTERSPEECH 2017
Bio
Zvi Kons is a researcher in the Speech Technologies group at IBM Haifa Research Lab. His main interest is speech classification, speech synthesis and speech processing.
Zvi received his B.A. and M.Sc. in Physics from the Technion, Israel Institute of Technology, Haifa, Israel, in 1992 and 1999, respectively.
Previous experience includes research and development in areas of signal processing, image processing and computer vision. He joined IBM at 2001 and for several years lead the IBM embedded Text-to-Speech project.
Publications
Enhancing decision-level fusion through cluster-based partitioning of feature set
- Evaldas Vaiciukynas
- Antanas Verikas
- et al.
- 2014
- MENDEL 2014
Fusion of voice signal information for detection of mild laryngeal pathology
- Evaldas Vaiciukynas
- Antanas Verikas
- et al.
- 2014
- Applied Soft Computing Journal
Voice transformation-based spoofing of text-dependent speaker verification systems
- Zvi Kons
- Hagai Aronowitz
- 2013
- INTERSPEECH 2013
Audio event classification using deep neural networks
- Zvi Kons
- Orith Toledo-Ronen
- 2013
- INTERSPEECH 2013
A hybrid text-to-speech system that combines concatenative and statistical synthesis units
- Stas Tiomkin
- David Malah
- et al.
- 2011
- IEEE Transactions on Audio, Speech and Language Processing
Reducing the footprint of the IBM trainable speech synthesis system
- Dan Chazan
- Ron Hoory
- et al.
- 2002
- ICSLP 2002
Patents
Top collaborators
RH
Ron Hoory
STSM, Speech Team lead, IBM Research - Haifa
ST
Samuel Thomas
Senior Research Scientist - Speech Recognition and Spoken Language Understanding
GK
Gakuto Kurata
Distinguished Engineer and Chief Scientist for Spoken Conversational Systems
RB
Roy Bar-Haim
Senior Technical Staff Member - AI, Natural Language Processing