Cross-lingual and multi-stream posterior features for low resource LVCSR systems

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

Volumn , Issue , 2010, Pages 877-880

  Thomas, Samuel ^a   Ganapathy, Sriram ^a   Hermansky, Hynek ^a  

^a Johns Hopkins University   (United States)

Author keywords

Cross lingual posterior features; Low resource ASR; Multi stream features; Tandem features

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; MULTILAYER NEURAL NETWORKS; SPEECH COMMUNICATION; SPEECH PROCESSING;

CONVERSATIONAL TELEPHONE SPEECH; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; LOW RESOURCE ASR; MULTI-LAYER PERCEPTRONS (MLPS); MULTI-STREAM; POSTERIOR FEATURES; SOURCES OF INFORMATIONS; TANDEM FEATURES; CROSS-LINGUAL; CROSS-LINGUAL POSTERIOR FEATURE; MULTI-STREAM FEATURE; SPEECH RECOGNITION SYSTEMS; TANDEM FEATURE;

DATA STREAMS; CONTINUOUS SPEECH RECOGNITION;

EID: 79959819891     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (16)

1. S. Davis and P. Mermelstein, "Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences", IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 28, no. 4, pp. 357-366, 1980. (Pubitemid 11464930)
2. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech", The Journal of the Acoustical Society of America, vol. 87, pp. 1738-1752, 1990. (Pubitemid 20256470)
3. H. Hermansky, D.P.W. Ellis and S. Sharma, "Tandem con-nectionist feature extraction for conventional HMM systems", in IEEE ICASSP, 2000, pp. 1635-1638.
4. G. Zavaliagkos et al., "Using Untranscribed Training Data to Improve Performance", in ISCA ICSLP, 1998.
5. S. Thomas, S. Ganapathy and H. Hermansky, "Tandem Representations of Spectral Envelope and Modulation Frequency Features for ASR", in ISCA INTERSPEECH, 2009.
6. S. Sivadas and H. Hermansky, "On use of task independent training data in tandem feature extraction", in IEEE ICASSP, 2004, pp. 541-544.
7. Q. Zhu, B. Chen, N. Morgan and A. Stolcke, "On using MLP features in LVCSR", in ISCA INTERSPEECH, 2004, pp. 921-924.
8. A. Stolcke et. al., "Cross-domain and cross-language portability of acoustic features estimated by multilayer perceptrons", in IEEE ICASSP, 2006, pp. 321-324.
9. A. Canavan, D. Graff, and G. Zipperlen, "CALLHOME American English Speech," Linguistic Data Consortium, 1997.
10. A. Canavan, D. Graff, and G. Zipperlen, "CALLHOME German Speech," Linguistic Data Consortium, 1997.
11. A. Canavan and G. Zipperlen, "CALLHOME Spanish Speech," Linguistic Data Consortium, 1997.
12. M.D. Richard and R.P. Lippmann, "Neural network classifiers estimate Bayesian a posteriori probabilities", Neural Computation, vol. 3, pp. 461-483, 1991.
13. J.J. Godfrey et al., "Switchboard: Telephone speech corpus for research and development," in IEEE ICASSP, 1992, pp. 517-520.
14. D. Graff. "English Gigaword", Linguistic Data Consortium, 2003.
15. F. Valente and H. Hermansky, "Combination of Acoustic Classifiers based on Dempster-Shafer Theory of Evidence," in IEEE ICASSP, 2007, pp. 1129-1132.
16. L. Burget et. al., "Multilingual Acoustic Modeling for Speech Recognition based on Subspace Gaussian Mixture Models", in IEEE ICASSP, 2010.