Sotabase

Career

· Distinguished Research Staff Member, IBM Research AI2019–2019
· Research Professor, NYU Courant-Computer Science and Center for Data Science2019–
· Senior Manager, IBM Research1998–2019
· Associate Member, IBM Haifa Research Lab1985–2019
· Research Staff Member, IBM Research1981–1984
· Student Co-op, Verbex1979–1980
· Doctor of Science (Sc.D.), Massachusetts Institute of Technology1975–1981
· Master of Science (S.M.), Massachusetts Institute of Technology1975–1978
· Bachelor of Science (S.B.), Massachusetts Institute of Technology1971–1975

Publications (406)

Speaking clearly for the hard of hearing. II: Acoustic characteristics of clear and conversational speech.
Journal of Speech and Hearing Research · 1986
715
cited
Speaker adaptation of neural network acoustic models using i-vectors
2013 IEEE Workshop on Automatic Speech Recognition and Understanding · 2013
674
cited
Speaking clearly for the hard of hearing I: Intelligibility differences between clear and conversational speech.
Journal of Speech and Hearing Research · 1985
535
cited
English Conversational Telephone Speech Recognition by Humans and Machines
Interspeech · 2017
371
cited
Deep Belief Networks using discriminative features for phone recognition
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2011
314
cited
Speech recognition using noise-adaptive prototypes
ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing · 1988
223
cited
Speaking clearly for the hard of hearing. III: An attempt to determine the contribution of speaking rate to differences in intelligibility between clear and conversational speech.
Journal of Speech and Hearing Research · 1989
161
cited
Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2017
153
cited
Decision trees for phonological rules in continuous speech
IEEE International Conference on Acoustics, Speech, and Signal Processing · 1991
153
cited
Automatic recognition of spontaneous speech for access to multilingual oral history archives
IEEE Transactions on Speech and Audio Processing · 2004
148
cited
AVLnet: Learning Audio-Visual Language Representations from Instructional Videos
Interspeech · 2020
146
cited
The IBM expressive text-to-speech synthesis system for American English
IEEE Transactions on Audio, Speech, and Language Processing · 2006
143
cited
The IBM 2015 English conversational telephone speech recognition system
Interspeech · 2015
132
cited
Robust methods for using context-dependent features and models in a continuous speech recognizer
Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing · 1994
114
cited
Speaking clearly for the hard of hearing
1979
113
cited
Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task
IEEE International Conference on Acoustics, Speech, and Signal Processing · 1995
107
cited
Multilingual representations for low resource speech recognition and keyword search
Automatic Speech Recognition & Understanding · 2015
103
cited
Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks
Neural Information Processing Systems · 2018
100
cited
New methods in continuous Mandarin speech recognition
EUROSPEECH · 1997
98
cited
Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos
IEEE International Conference on Computer Vision · 2021
97
cited
Sotabase