Using MLP features in SRI's conversational speech recognition system

9th European Conference on Speech Communication and Technology

Volumn , Issue , 2005, Pages 2141-2144

  Zhu, Qifeng ^a   Stolcke, Andreas ^a,b   Chen, Barry Y ^a,c   Morgan, Nelson ^a,c  

^a INTERNATIONAL COMPUTER SCIENCE INSTITUTE   (United States)

^b SRI INTERNATIONAL   (United States)

^c UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CONVERSATIONAL TELEPHONE SPEECH (CTS); MULTILAYER PERCEPTRONS (MLP); WORD ERROR RATE (WER);

ACOUSTIC SIGNAL PROCESSING; BIT ERROR RATE; PROBABILITY; SPEECH SYNTHESIS; TELEPHONE SYSTEMS;

SPEECH RECOGNITION;

EID: 33745185321     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. N. Morgan, B. Y. Chen, Q. Zhu, and A. Stolcke, "TRAPping conversational speech: Extending TRAP/Tandem approaches to conversational telephone speech recognition," in Proc. ICASSP, Montreal, May 2004, vol. 1, pp. 536-539.
2. Q. Zhu, B. Y. Chen, and N. Morgan, "On using MLP features in LVCSR," in Proc. ICSLP, S. H. Kim and D. H. Youn, Eds., Jeju, Korea, Oct. 2004.
3. H. Hermansky and S. Sharma, "Temporal patterns (TRAPS) in ASR of noisy speech," in Proc. ICASSP, Phoenix, AZ, Mar. 1999, vol. 2, pp. 289-292.
4. B. Chen, S. Chang, and S. Sivadas, "Learning discriminative temporal patterns in speech: Development of novel TRAPS-like classifiers," in Proc. EUROSPEECH, P. Dalsgaard, B. Lindberg, H. Benner, and Z. Tan, Eds., Aalborg, Denmark, Sept. 2001, vol. 1, pp. 429-432.
5. H. Hermansky, D. Ellis, and S. Sharma, "Tandem connectionist feature stream extraction for conventional HMM systems," in Proc. ICASSP, Istanbul, June 2000, vol. III, pp. 1635-1638.
6. D. Ellis and N. Morgan, "Size matters: An empirical study of neural network training for large vocabulary continuous speech recognition," in Proc. ICASSP, Phoenix, AZ, Mar. 1999, vol. II, pp. 1013-1016.
7. A. Stolcke et al., "SRI/ICSI/UW Fall 2004 conversational telephone speech-to-text system," DARPA RT-04F Workshop, Nov. 2004.
8. M. Graciarena, H. Franco, J. Zheng, D. Vergyri, and A. Stolcke, "Voicing feature integration in SRI's Decipher LVCSR system," in Proc. ICASSP, Montreal, May 2004, vol. 1, pp. 921-924.
9. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," J. Acoust. Soc. Am., vol. 87, no. 4, pp. 1738-1752, Apr. 1990.
10. I. Bulyko, M. Ostendorf, and A. Stolcke, "Getting more mileage from web text sources for conversational speech language modeling using class-dependent mixtures," in Proc. HLT-NAACL 2003, M. Hearst and M. Ostendorf, Eds., Edmonton, Alberta, Canada, Mar. 2003, vol. 2, pp. 7-9, Association for Computational Linguistics.
11. D. Povey and P. C. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. ICASSP, Orlando, FL, May 2002, vol. 1, pp. 105-108.