Analysis and comparison of recent MLP features for LVCSR systems

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

Volumn , Issue , 2011, Pages 1245-1248

  Valente, Fabio ^a   Magimai Doss, Mathew ^a   Wang, Wen ^b  

^a IDIAP RESEARCH INSTITUTE   (Switzerland)

^b SRI INTERNATIONAL   (United States)

Author keywords

Acoustic features; GALE project; LVCSR; Multilayer Perceptron; TANDEM features

Indexed keywords

ACOUSTIC FEATURES; GALE PROJECT; LVCSR; MULTI LAYER PERCEPTRON; TANDEM FEATURES;

COMPUTER APPLICATIONS; COMPUTER SIMULATION;

SPEECH RECOGNITION;

EID: 84865734256     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. Hermansky H., Ellis D., and Sharma S., "Connectionist feature extraction for conventional hmm systems.," Proceedings of ICASSP, 2000.
2. Morgan N. et al., "Pushing the envelope - aside," IEEE Signal Processing Magazine, vol. 22, no. 5, 2005.
3. Hermansky H. and Fousek P., "Multi-resolution rasta filtering for tandembased asr.," in Proceedings of Interspeech 2005, 2005.
4. Schwarz P., Matejka P., and Cernocky J., "Extraction of features for automatic recognition of speech based on spectral dynamics," in Proceedings of TSD04, Brno, Czech Republic, September 2004, pp. 465 - 472.
5. Fousek P., Extraction of Features for Automatic Recognition of Speech Based on Spectral Dynamics, Ph.D. thesis, Czech Technical University in Prague, Faculty of Electrical Engineering, 2007.
6. Grezl F., Karafiat M., Kontar S., and Cernocky J., "Probabilistic and bottle-neck features for lvcsr of meetings," in Proceedings of ICASSP07,Hononulu, 2007.
7. Valente F., Magimai-Doss M., Plahl C., Ravuri S., and Wang W., "A Comparative Study of MLP Front-ends for Mandarin ASR ," in Proceedings of Interpseech, 2010.
8. Hermansky H. and Tibrewala S., "Towards ASR on partially corrupted speech," Proc. ICSLP, 1996.
9. Hwang M.-Y., Gang P., Ostendorf M., Wang W., Faria A., and Heidel A., "Building a highly accurate mandarin speech recognizer with languageindependent technologies and language-dependent modules," IEEE Transaction on Audio, Speech and Language Processing, vol. 17, no. 7, 2009.
10. Lei X., Siu S., Hwang M.-Y., Ostendorf M., and Lee T., "Improved Tone Modeling for Mandarin Broadcast News Speech Recognition .," Proceedings of Interspeech, 2006.
11. Hermansky H. and Sharma S., "Temporal Patterns (TRAPS) in ASR of Noisy Speech," in Proceedings of ICASSP'99, Phoenix, Arizona, USA, 1999.
12. Marios Athineos, Hynek Hermansky, and Daniel P.W. Ellis, "Lp-trap: Linear predictive temporal patterns," in Proc. ICSLP, 2004, pp. 1154-1157.
13. Grezl F. and Fousek P., "Optimizing bottleneck features for lvcsr," in Proceedings of ICASSP08,Las Vegas, 2008.
14. Valente F. and Hermansky H., "Combination of Acoustic Classifiers based on Dempster-Shafer Theory of Evidence," Proc. ICASSP, 2007.