Decoding network optimization using minimum transition error training

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2012, Pages 4197-4200

  Kubo, Yotaro ^a   Watanabe, Shinji ^a,b   Nakamura, Atsushi ^a  

^a Nippon Telegraph and Telephone Corporation   (Japan)

^b MITSUBISHI ELECTRIC RESEARCH LABORATORIES   (United States)

Author keywords

Automatic speech recognition; conditional random fields; transition errors; weighed finite state transducers

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; AUTOMATIC SPEECH RECOGNIZERS; CONDITIONAL RANDOM FIELD; CONDITIONAL RANDOM FIELDS (CRFS); DECODING PROCESS; ERROR MINIMIZATION; FINITE STATE TRANSDUCERS; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; LINEAR CLASSIFICATION; MAXIMUM MUTUAL INFORMATION; NETWORK OPTIMIZATION; STATE TRANSITIONS; TRAINING METHODS; TRAINING TECHNIQUES; WEIGHTED FINITE-STATE TRANSDUCERS;

CONTINUOUS SPEECH RECOGNITION; ERRORS; IMAGE SEGMENTATION; OPTIMIZATION; RANDOM PROCESSES; SIGNAL PROCESSING; STEREOPHONIC BROADCASTING; TRANSDUCERS;

DECODING;

EID: 84865213310     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2012.6288844     Document Type: Conference Paper

References (11)

1. A. Gunawardana, M. Mahajan, A. Acero, and J. C. Platt, "Hidden conditional random fields for phone classification," in Proc. INTERSPEECH, 2005.
2. G. Zweig and P. Nguyen, "A segmental CRF approach to large vocabulary continuous speech recognition," in Proc. IEEE ASRU, 2009, pp. 152-157.
3. S.Watanabe, T. Hori, and A. Nakamura, "Large vocabulary continuous speech recognition using WFST-based linear classifier for structured data," in Proc. INTERSPEECH, Aug. 2010, pp. 346-349.
4. M. Lehr and I. Shafran, "Learning a discriminative weighted finite state transducer for automatic speech recognition," IEEE Trans. ASLP, vol. 19, pp. 1360-1367, 2011.
5. D. Povey, D. Kanevsky, B. Kingsbury, B. Ramabhadran, G. Saon, and K. Visweswariah, "Boosted MMI for model and feature-space discriminative training," in Proc. ICASSP-2008, 2008, pp. 4057-4060.
6. E. McDermott, S. Watanabe, and N. Atsushi, "Discriminative training based on an integrated view of MPE and MMI in margin and error space," in Proc. ICASSP-2010, 2010.
7. E. McDermott and S. Katagiri, "String-level MCE for continuous phoneme recognition," in Proc. EUROSPEECH, 1997.
8. D. Povey and P. C.Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. ICASSP, 2002, vol. 1, pp. I-105.
9. J. Glass, T. J. Hazen, S. Cyphers, I. Malioutov, D. Huynh, and R. Barzilay, "Recent progress in the MIT Spoken Lecture Processing Project," in Proc. INTERSPEECH, 2007, pp. 2553-2556.
10. T. Hori, C. Hori, Y. Minami, and A. Nakamura, "Efficient WFST-based one-pass decoding with on-the-fly hypothesis rescoring in extremely large vocabulary continuous speech recognition," IEEE Trans. ASLP, vol. 15, pp. 1352-1365, 2007.
11. M. Riedmiller and H. Braun, "A direct adaptive method for faster back-propagation learning: The Rprop algorithm," in Proc. IEEE ICNN, 1993, pp. 586-591.