Ananth Sankar
Ananth Sankar
Verified email at linkedin.com
Title
Cited by
Cited by
Year
A maximum-likelihood approach to stochastic matching for robust speech recognition
A Sankar, CH Lee
IEEE transactions on speech and Audio Processing 4 (3), 190-202, 1996
5171996
Method and system for learning linguistically valid word pronunciations from acoustic data
F Beaufays, A Sankar, M Weintraub, S Williams
US Patent 7,266,495, 2007
1662007
System and method for joint speaker and scene recognition in a video/audio processing environment
JC Chou, S Kajarekar, JJ Catchpole, A Sankar
US Patent App. 13/469,886, 2013
1422013
Bayesian model combination (baycom) for improved recognition
A Sankar
Proceedings.(ICASSP'05). IEEE International Conference on Acoustics, Speech …, 2005
1362005
Efficient lattice representation and generation
F Weng, A Stolcke, A Sankar
In Proc. of ICSLP, 1998
1271998
MAESTRO: Conductor of multimedia analysis technologies
C The SRI MAESTRO Team
Communications of the ACM 43 (2), 57-63, 2000
1172000
A comparative study of speaker adaptation techniques
L Neumeyer, A Sankar, V Digalakis
system 1, 2, 1995
1101995
Robust speech recognition based on stochastic matching
A Sankar, CH Lee
1995 International Conference on Acoustics, Speech, and Signal Processing 1 …, 1995
981995
Connectionist speaker normalization and adaptation
V Abrash, H Franco, A Sankar, M Cohen
in Eurospeech, 1995
871995
An experiment in spoken language acquisition
AL Gorin, SE Levinson, A Sankar
IEEE Transactions on Speech and Audio Processing 2 (1), 224-240, 1994
741994
Neural tree networks
A Sankar
Neural networks: theory and applications, 281-302, 1991
721991
Rapidly trainable neural tree network
RJ Mammone, A Sankar, KR Farrell
US Patent 5,634,087, 1997
621997
Experiments with a Gaussian merging-splitting algorithm for HMM training for speech recognition
A Sankar
Proceedings of DARPA Speech Recognition Workshop, 99-104, 1998
551998
Optimal pruning of neural tree networks for improved generalization
A Sankar, RJ Mammone
IJCNN-91-Seattle International Joint Conference on Neural Networks 2, 219-224, 1991
551991
Speaker segmentation and recognition based on list of speakers
A Sankar, S Kajarekar, SK Gannu
US Patent 9,058,806, 2015
542015
Rapid speech recognizer adaptation to new speakers
V Digalakis, H Collier, S Berkowitz, A Corduneanu, E Bocchieri, A Kannan, ...
1999 IEEE International Conference on Acoustics, Speech, and Signal …, 1999
521999
Word-level rate of speech modeling using rate-specific phones and pronunciations
J Zheng, H Franco, F Weng, A Sankar, H Bratt
2000 IEEE International Conference on Acoustics, Speech, and Signal …, 2000
422000
The development of SRI’s 1997 Broadcast News transcription system
A Sankar, F Weng, Z Rivlin, A Stolcke, RR Gadde
Proceedings DARPA Broadcast News Transcription and Understanding Workshop, 91-96, 1998
421998
Training data clustering for improved speech recognition.
A Sankar, F Beaufays, V Digalakis
EUROSPEECH, 1995
421995
Method of and apparatus for signal recognition that compensates for mismatching
C Lee, A Sankar
US Patent 5,727,124, 1998
391998
The system can't perform the operation now. Try again later.
Articles 1–20