Posterior-scaled MPE: Novel discriminative training criteria

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

Volumn 3, Issue , 2012, Pages 2613-2616

  Nussbaum Thom, Markus ^a   Tüske, Zoltán ^a   Heigold, Georg ^b   Schlüter, Ralf ^a   Ney, Hermann ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

^b GOOGLE INC   (United States)

Author keywords

Discriminative training criteria; Error bounds; Margin; MPE

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; DISCRIMINATIVE TRAINING; ERROR BOUND; GLOBAL ERRORS; LOSS FUNCTIONS; MARGIN; MPE; NON-TRIVIAL;

COMPUTER APPLICATIONS; COMPUTER SIMULATION;

ERROR ANALYSIS;

EID: 84878563380     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. R. Schlüter, "Investigations on Discriminative Training Criteria", PhD thesis, RWTH Aachen University, Aachen, Germany, September, 2000.
2. E. McDermott, and S. Watanabe and A. Nakamura, "Margin-space integration of MPE loss via differencing of MMI functionals for generalized error-weighted discriminative training", Interspeech, pp. 224-227, 2009.
3. G. Heigold, "A Log-Linear Discriminative Modeling Framework for Speech Recognition", PhD thesis, RWTH Aachen University, Aachen, Germany, June, 2010.
4. M. Nussbaum-Thom, G. Heigold, R. Schlüter, H. Ney, "On the Relation of Loss-Based Error Bounds to Discriminative Training Criteria", submitted to the Neural Information Processing Systems (NIPS) Conference, 2012. (Available by personal communication in the case of rejection.)
5. J. Eisner, "Expectation semirings: Flexible EM for finite-state transducers" Finite-State Methods and Natural Language Processing (FSMNLP), Helsinki, Finland, 2001.
6. H. Ney, "On the Relationship between Classification Error Bounds and Training Criteria in Statistical Pattern Recognition", Iberian Conference on Pattern Recognition and Image Analysis IbPRIA, Puerto de Andratx, Spain, 636-645, June, 2003.
7. G. Heigold, T. Deselaers, R. Schlüter and H. Ney, "Modified MMI/MPE: A Direct Evaluation of the Margin in Speech Recognition", ICML, pp. 384-391, Helsinki, Finland, July, 2008.
8. M. Nussbaum-Thom, S.Wiesler, G. Heigold, R. Schlüter, H. Ney, "Novel Error Bounds and Discriminative Training Criteria", submitted to Interspeech 2012.
9. R. Bracewell, "The Sifting Property", In The Fourier Transform and Its Applications, 3rd ed. New York, McGraw-Hill, pp. 74-77, 1999.
10. M. Gibson, "Minimum Bayes risk acoustic model estimation and adaptation", PhD thesis, University of Sheffield, Sheffield, UK, 2008.
11. K.-F. Lee and H.-W. Hon,"Speaker-independent phone recognition using hidden Markov models",IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 37, no. 11, pp. 1641-1648, 1989.