A multistream multiresolution framework for phoneme recognition

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 318-321

  Mesgarani, Nima ^a   Thomas, Samuel ^a   Hermansky, Hynek ^a  

^a Johns Hopkins University   (United States)

Author keywords

Multistream; Spectrotemporal modulations; Speech recognition

Indexed keywords

SPEECH COMMUNICATION; SPEECH PROCESSING; SYSTEMATIC ERRORS;

INTUITIVE UNDERSTANDING; MULTI-STREAM; PHONEME RECOGNITION; POSTERIOR PROBABILITY; ROBUST PHONEME RECOGNITION; SPEAKER RECOGNITION; SPECTRO-TEMPORAL MODULATIONS; SPEECH PROCESSING TECHNOLOGIES; HIGH DIMENSIONALITY; MULTIRESOLUTION; PHONEMES RECOGNITION; SPECTROTEMPORAL MODULATIONS; STREAM-BASED;

SPEECH RECOGNITION;

EID: 79959816304     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Hermansky, H., Fousek, P., "Multi-resolution rasta filtering for tandem-based asr", In Proceedings of Interspeech, Lisbon, Portugal, pp. 361-364, 2005. (Pubitemid 43908074)
2. S. Tibrewala and H. Hermansky, "Multi-Stream Approach in Acoustic Modeling", in LVCSR-Hub5 Workshop, May, 1997
3. Bourlard, H. and Dupont, S., "A new ASR approach based on independent processing and recombination of partial frequency bands", In Proc. of Intl. Conf. on Spoken Language Processing.
4. Andrew C. Morris, Astrid Hagen, Hervé Glotin, and Hervé Bourlard, "Multi-stream adaptive evidence combination for noise robust ASR," Speech Comm., vol. 34, pp. 25-40, 2001. (Pubitemid 32874681)
5. Misra, H., Bourlard, H., Tyagi, V., "New entropy based combination rules in HMM/ANN multi-stream ASR, in Proc. ICASSP, pp. II-741-4 vol.2, Hong Kong, 2003
6. Sherry Y. Zhao, Suman Ravuri, Nelson Morgan, "Multi-Stream to Many-Stream: Using Spectro-Temporal Features for ASR", in proceeding of ICASSP 2010, Dallas, Texas
7. F. Valente and H. Hermansky, "Multi-stream Features Combination based on Dempster-Shafer Rule for LVCSR System", in Proceedings of the International Conference on Spoken Language Processing, Antwerp, Belgium 2007.
8. T. Chi, P. Ru, S. A. Shamma, Multiresolution spectrotemporal analysis of complex sounds, J Acoust Soc Am. 2005 Aug; 118(2):887-906. (Pubitemid 41129224)
9. Mesgarani, N., David, S, S. A. Shamma, "Representation of phonemes in primary auditory cortex: how the brain analyzes speech", IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP), Hawaii, April 2007
10. Mesgarani, N., Slaney, M., and Shamma, S., "Discrimination of speech from nonspeech based on multiscale spectro-temporal modulations", IEEE Trans. Audio, Speech, and Language Proc., 14(3):920-929, 2006.
11. Michael Kleinschmidt, "Localized spectro-temporal features for automatic speech recognition", EUROSPEECH 2003.