Data-driven clustered hierarchical tandem system for LVCSR

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2008, Pages 2250-2253

  Chang, Shuo Yiin ^a   Lee, Lin Shan ^a  

^a NATIONAL TAIWAN UNIVERSITY   (Taiwan)

Author keywords

[No Author keywords available]

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; BROADCAST NEWS; DATA-DRIVEN; ERROR RATE REDUCTION; GLOBAL LEARNING; HIERARCHICAL STRUCTURES; MLP CLASSIFIERS; MULTI LAYER PERCEPTRON; TANDEM SYSTEM;

CLASSIFIERS; FEATURE EXTRACTION; SPEECH COMMUNICATION;

SPEECH RECOGNITION;

EID: 84867196296     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Hermansky, H., Ellis, D.P.W. and Sharma, S., "Tandem connectionist feature extraction for conventional HMM systems", ICASSP 2000
2. Bourlard, H. and Morgan, N., "Connectionist speech recognition: A hybrid approach", Kluwer Academic Publishers, Boston, USA, 1994
3. Zhu, Q., Chen, B., Morgan, N., and Stolcke, A., "On using MLP features in LVCSR", ICSLP 2004
4. Chen, B., Zhu, Q., Morgan, N. "Learning long term temporal features in LVCSR using neural networks", ICSLP 2004
5. Hermansky, H., Ellis, "TRAP-TANDEM: Data-driven extraction of temporal features from speech", ASRU 2003
6. Q. Zhu, A. Stolcke, B. Y. Chen, and N. Morgan, "Incorporating Tandem/HATs MLP features into SRI's conversational speech recognition system," EARS RT-04F Workshop, 2004
7. Zhu, Q., Stolcke, A., Chen, B., and Morgan, N, "Improved MLP structures for data-driven feature extraction for ASR", Interspeech 2005
8. Schwarz, P., Matejka, P., Cernock J., "Hierarchical structures of neural networks for phoneme recognition", ICASSP 2006
9. Antoniou, C., "Modular neural networks exploit large acoustic context through broad-class posteriors for continuous speech recognition", ICASSP 2001
10. Fritsch, J. "ACID/HNN - Clustering hierarchies of neural networks for context-dependent connectionist acoustic modelling", ICASSP 1998
11. Sivadas, S. and Hermansky, H., "Hierarchical tandem feature extraction", ICASSP 2002
12. Fabio Valente, Jithendra Vepa1, Christian Plahl, Christian Gollan, Hermansky, H., Ralf Schlüter, "Hierarchical neural networks feature extraction for LVCSR system", Interspeech 2007
13. X. Lei, M.-Y. Hwang, and M. Ostendorf, "Incorporating tone-related MLP posteriors in the feature representation for Mandarin ASR," Interspeech 2005
14. M.-Y. Hwang, Gang Peng, Wen Wang, Arlo Faria, Aaron Heidel, Mari Ostendorf, "Building a highly accurate Mandarin speech recognizer," ASRU 2007
15. H. Misra, H. Bourlard, and V. Tyagi, "New entropy based combination rules in HMM/ANN multi-stream ASR", ICASSP 2003.