Sledovat
Hynek Hermansky
Hynek Hermansky
Julian S. Smith Professor in Electrical Engineering, The Johns Hopkins University
E-mailová adresa ověřena na: jhu.edu
Název
Citace
Citace
Rok
Perceptual linear predictive (PLP) analysis of speech
H Hermansky
the Journal of the Acoustical Society of America 87 (4), 1738-1752, 1990
43411990
RASTA processing of speech
H Hermansky, N Morgan
IEEE transactions on speech and audio processing 2 (4), 578-589, 1994
28031994
Tandem connectionist feature extraction for conventional HMM systems
H Hermansky, DPW Ellis, S Sharma
2000 IEEE international conference on acoustics, speech, and signal …, 2000
9872000
RASTA-PLP speech analysis
H Hermansky, N Morgan, A Bayya, P Kohn
Proc. IEEE Int’l Conf. Acoustics, speech and signal processing 1, 121-124, 1991
5851991
Recognition of speech in additive and convolutional noise based on RASTA spectral processing
H Hermansky, N Morgan, HG Hirsch
1993 IEEE International Conference on Acoustics, Speech, and Signal …, 1993
3951993
Should recognizers have ears?
H Hermansky
Speech communication 25 (1-3), 3-27, 1998
2981998
Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP).
H Hermansky, N Morgan, A Bayya, P Kohn
Eurospeech 91, 1367-1370, 1991
2861991
Temporal patterns (TRAPS) in ASR of noisy speech
H Hermansky, S Sharma
1999 IEEE International Conference on Acoustics, Speech, and Signal …, 1999
2701999
Towards increasing speech recognition error rates
H Bourlard, H Hermansky, N Morgan
Speech communication 18 (3), 205-231, 1996
2621996
The challenge of spoken language systems: Research directions for the nineties
R Cole, L Hirschman, L Atlas, M Beckman, A Biermann, M Bush, ...
IEEE transactions on Speech and Audio processing 3 (1), 1-21, 1995
2601995
Towards ASR on partially corrupted speech
H Hermansky, S Tibrewala, M Pavel
Proceeding of Fourth International Conference on Spoken Language Processing …, 1996
2501996
Traps-classifiers of temporal patterns
H Hermansky, S Sharma
Fifth International Conference on Spoken Language Processing, 1998
2301998
Sub-band based recognition of noisy speech
S Tibrewala, H Hermansky
1997 IEEE International Conference on Acoustics, Speech, and Signal …, 1997
2071997
Spectral entropy based feature for robust ASR
H Misra, S Ikbal, H Bourlard, H Hermansky
2004 IEEE International Conference on Acoustics, Speech, and Signal …, 2004
1922004
Towards spoken term discovery at scale with zero resources
A Jansen, K Church, H Hermansky
Eleventh Annual Conference of the International Speech Communication Association, 2010
1792010
Qualcomm-ICSI-OGI features for ASR.
AG Adami, L Burget, S Dupont, H Garudadri, F Grezl, H Hermansky, ...
INTERSPEECH, 2002
1782002
Noise resistant auditory model for parametrization of speech
H Hermansky, NH Morgan
US Patent 5,537,647, 1996
1771996
Multi-resolution RASTA filtering for TANDEM-based ASR
H Hermansky, P Fousek
IDIAP, 2005
1712005
Deep neural network features and semi-supervised training for low resource speech recognition
S Thomas, ML Seltzer, K Church, H Hermansky
2013 IEEE international conference on acoustics, speech and signal …, 2013
1692013
On the relative importance of various components of the modulation spectrum for automatic speech recognition
N Kanedera, T Arai, H Hermansky, M Pavel
Speech Communication 28 (1), 43-55, 1999
1671999
Systém momentálně nemůže danou operaci provést. Zkuste to znovu později.
Články 1–20