Improved discriminative training using phone lattices

9th European Conference on Speech Communication and Technology

Volumn , Issue , 2005, Pages 2125-2128

  Zheng, Jing ^a   Stolcke, Andreas ^a  

^a SRI INTERNATIONAL   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CONVERSATIONAL TELEPHONE SPEECH; MINIMUM PHONE FRAME ERROR (MPFE); PHONE LATTICES; WORD ERROR RATE (WER);

BIT ERROR RATE; PERSONNEL TRAINING; SPEECH PROCESSING; SPEECH RECOGNITION; STATISTICAL METHODS; STEREOPHONIC BROADCASTING;

SPEECH INTELLIGIBILITY;

EID: 33745203493     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. L.R. Bahl, P.F. Brown, P.V. de Souza and R.L. Mercer, "Maximum Mutual Information Estimation of Hidden Markov Model Parameters for Speech Recognition," Proc. ICASSP'86, pp. 49-52, Tokyo, 1986.
2. P.C. Woodland and D. Povey, "Large Scale Discriminative Training of Hidden Markov Models of Speech Recognition," Computer Speech & Language, Vol. 16, pp. 25-47, 2002.
3. D. Povey and P.C. Woodland, "Minimum Phone Error and I-Smoothing for Improved Discriminative Training," Proc. ICASSP'02, Orlando, 2002.
4. J. Huang, B. Kingsbury, L. Mangu, G. Saon, R. Sarikaya and G. Zweig, "Improvements to the IBM Hub-5E System," Proc. NIST RT-02 Workshop, 2002.
5. M. Morhri, "Finite-State Transducers in Language and Speech Processing," Computational Linguistics, 23(2): 269-312, 1997.
6. A. Ljolje, F. Pereira and M. Riley, "Efficient General Lattice Generation and Rescoring," Proc. EUROSPEECH'99, Budapest, 1999.
7. M. Graciarena, H. Franco, J. Zheng, D. Vergyri and A. Stolcke, "Voicing Feature Integration in SRI's Decipher LVCSR System," Proc. ICASSP'04, Vol. 1, pp. 921-924, Montreal, 2004.
8. L. Mangu, E. Brill and A. Stolcke, "Searching for Consensus to Improve Recognition Output," Proc. Hub-5 Conversational Speech Recognition Workshop, Linthicum Heights, 1998.
9. G. Evermann and P.C. Woodland, "Posterior Probability Decoding, Confidence Estimation and System Combination," Proc. Speech Transcription Workshop, College Park, 2000.
10. Q. Zhu, A. Stolcke, B. Chen and N. Morgan, "Incorporating TANDEM/HATS MLP Features into SRI's Conversational Speech Recognition System," Proc. EARS RT04 Workshop, Palisades, 2004.
11. M. J. F. Gales, "Maximum Likelihood Linear Transformations for HMM-based Speech Recognition," Computer Speech and Language, Vol. 12, pp 75-98, 1998.
12. SRI system description, EARS RT04 Workshop, Palisades, 2004.