Publications

Found 11 results
Author Title Type [ Year(Asc)]
Filters: First Letter Of Title is S and Author is Hynek Hermansky  [Clear All Filters]
2008
Ganapathy, S., Motlicek P., Hermansky H., & Garudadri H. (2008).  Spectral Noise Shaping: Improvements in Speech/Audio Codec Based on Linear Prediction in Spectral Domain.
2004
Hermansky, H., & Morgan N. (2004).  Show What You Know: Musings on the Reporting of Negative Results in Speech Recognition Research. Journal of Negative Results in Speech and Audio Sciences. 1,
Morgan, N., Bourlard H., & Hermansky H. (2004).  Speech Recognition and the Auditory Perspective.
2001
Kajarekar, S., Yegnanarayana B.., & Hermansky H. (2001).  A Study of Two Dimensional Linear Descriminants For ASR. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2001).
2000
Yang, H. Hua, & Hermansky H. (2000).  Search for Information Bearing Components in Speech. 12,
1999
Arai, T., Pavel M., Hermansky H., & Avendano C. (1999).  Syllable Intelligibility for Temporally-Filtered LPC Cepstral Trajectories. Journal of the Acoustical Society of America. 105(5), 2783-2791.
1998
Hermansky, H., & Malayath N.. (1998).  Spectral Basis Functions from Discriminant Analysis. Proceedings of the Fifth International Conference on Spoken Language Processing (ICSLP'98).
1997
Hermansky, H. (1997).  Should Recognizers Have Ears?. Proceedings of ESCA Tutorial and Research Workshop on Robust Speech Recognition for Unknown Communication Channels. 1-10.
1995
Morgan, N., Bourlard H., Greenberg S., Hermansky H., & Wu S-L. (1995).  Stochastic Perceptual Models of Speech. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 95).
1994
Morgan, N., Bourlard H., Greenberg S., & Hermansky H. (1994).  Stochastic Perceptual Auditory-Event-Based Models for Speech Recognition. Proceedings of the Third International Conference on Spoken Language Processing (ICSLP 94). 1943-1946.
1990
Morgan, N., Hermansky H., & Wooters C. (1990).  SPOONS '90: The SPeech recOgnition frOnt eNd workShop.