Publications
]
(1996). REMAP - Experiments with Speech Recognition.
Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP-96).
(1996). Speech Data Modeling at WS96: The Questionable Parameter Group.
Proceedings of the International Conference on Spoken Language Processing (ICSLP 96).
(1996). SPERT-II: A Vector Microprocessor System and Its Application to Large Problems in Backpropagation Training.
IEEE Computer. 29(3), 79-86.
(1996). Stochastic Perceptual Speech Models with Durational Dependence.
Proceedings of the Fourth International Conference on Spoken Language Processing (CSLP-96).
(1996). Towards Increasing Speech Recognition Error Rates.
Speech Communication. 205-231.
(1996). Towards Robustness to Fast Speech in ASR.
Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP-96).
(1996). Towards Subband-Based Speech Recognition.
Proceedings of the VIII European Signal Processing Conference (EUSIPCO '96). 1579-1582.
(1996). A Training Algorithm for Statistical Sequence Recognition with Applications to Transition-Based Speech Recognition.
IEEE Signal Processing Letters. 203-205.
(1997). Estimation of Global Posteriors and Forward-Backward Training of Hybrid HMM/ANN Systems.
Proceedings of the Fifth European Conference on Speech Communication and Technology (Eurospeech '97). 1951-1954.
(1997). Improving ASR Performance for Reverberant Speech.
Proceedings of the ESCA Workshop of Robust Speech Recognition. 87-90.
(1997). Integrating Syllable Boundary Information Into Speech Recognition.
The 22nd International Conference on Acoustics, Speech, and Signal Processing (ICASSP 1997). 2, 987-990.
(1997). Recognizing Reverberant Speech With RASTA-PLP.
The 22nd International Conference on Acoustics, Speech, and Signal Processing (ICASSP 1997). 2, 1259-1262.
(1997). Robust Features and Environmental Compensation: A Few Comments.
Proceedings of the ESCA Workshop of Robust Speech Recognition. 43-44.
(1997). Speech Recognition Using On-line Estimation of Speaking Rate.
Proceedings of the Fifth European Conference on Speech Communication and Technology (Eurospeech '97). 4, 2079-2082.
(1998). Combining Connectionist Multi-Band and Full-Band Probability Streams for Speech Recognition of Natural Numbers.
Proceedings of the Fifth International Conference on Spoken Language Processing (ICSLP '98). 743-746.
(1998). Combining Multiple Estimators of Speaking Rate.
Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 1998). 729-732.
(1998). Connectionist Techniques for Speech Recognition.
356-361.
(1998). Effects of Speaking Rate and Word Predictability on Conversational Pronunciations.
Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition.
(1998). Hybrid HMM/ANN Systems for Speech Recognition: Overview and New Research Directions.
389-417.
(1998). Incorporating Information from Syllable-length Time Scales into Automatic Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 1998). 721-724.
(1998). Performance Improvements Through Combining Phone- and Syllable-Length Information in Automatic Speech Recognition.
Proceedings of the Fifth International Conference on Spoken Language Processing (ICSLP'98). 854-857.
(1998). Robust Speech Recognition Using the Modulation Spectrogram.
Speech Communication. 25, 117-132.
(1998). Training Neural Networks with SPERT-II.
345-364.
(1998). Transmissions and Transitions: A Study of Two Common Assumptions in Multi-Band ASR.
Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 1998). 713-716.
(1999). Combined Speech and Speaker Recognition With Speaker-adapted Connectionist Models.
Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU-99).