Learning discriminative temporal patterns in speech: Development of novel TRAPS-like classifiers

EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology

Volumn , Issue , 2003, Pages 853-856

  Chen, Barry ^a,b   Chang, Shuangyu ^b   Sivadas, Sunil ^c  

^a INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^b UNIVERSITY OF CALIFORNIA   (United States)

^c OREGON HEALTH AND SCIENCE UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AUDITION;

CONTEXTUAL INFORMATION; CRITICAL BANDS; ENERGY PATTERNS; MULTI-LAYER PERCEPTRONS; NOISE CONDITIONS; PHONE RECOGNITION; TEMPORAL PATTERN; TEMPORAL PROCESSING;

SPEECH COMMUNICATION;

EID: 85009195248     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. Hermansky, H. and Sharma, S., "Temporal Patterns (TRAPS) in ASR of Noisy Speech", Proc. ICASSP 1999.
2. Hermansky, H.; Sharma, S.; Jain, P. "Data-Derived Nonlinear Mapping for Feature Extraction in HMM", Proc. ICASSP 2000.
3. Jain, P.; Hermansky, H.; Kingsbury B. "Distributed Speech Recognition Using Noise-Robust MFCC and TRAPS-Estimated Manner Features", Proc, ICSLP 2002.
4. Yang, H.; Sharma, S.; Van Vuren, S.; Hermansky, H. "Relevance of Time Frequency Features for Phonetic and Speaker Channel Classification", Speech Communication, August 2000.
5. Mirghafori, N. and Morgan, N., "Transmissions and Transitions: A Study of two Common Assumptions and Multiband ASR", Proc. ICASSP 1998.
6. Bourlard, H. and Morgan, N. Connectionist Speech Recognition: A Hybrid Approach, Kluwer Academic Publishers, 1994.
7. Robinson, T. and Christie, J., "Time-First Search for Large Vocabulary Speech Recognition", Proc. ICASSP 1998.
8. Lee, K. F. and Hon, H. W. "Speaker-Independent Phoneme Recognition Using Hidden Markov Models", IEEE Transactions on Acoustic Speech, and Signal Processing, 37(12), pp. 1641-1648, November 1989.
9. Hermansky, H., "Perceptual Linear Predictive (PLP) Analysis for Speech", The Journal of the Acoustical Society of America, 87:1738-1752, April 1990.
10. Antoniou, C., "Modular Neural Networks Exploit Large Acoustic Context Through Broad-Class Posteriors for Continuous Speech Recogition", Proc. ICASSP 2001