Modified MMI/MPE: A direct evaluation of the margin in speech recognition

Proceedings of the 25th International Conference on Machine Learning

Volumn , Issue , 2008, Pages 384-391

  Heigold, Georg ^a   Deselaers, Thomas ^a   Schlüter, Ralf ^a   Ney, Hermann ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

FEATURE EXTRACTION; LEARNING ALGORITHMS; LEARNING SYSTEMS; OPTIMIZATION; PROBABILITY DENSITY FUNCTION; ROBOT LEARNING; SPEECH; SPEECH ANALYSIS; STEREOPHONIC BROADCASTING; SUPPORT VECTOR MACHINES; TELEPHONE SETS; ALGORITHMS; FUNCTIONS; SPEECH RECOGNITION;

DISCRIMINATIVE TRAININGS; EFFICIENT ALGORITHMS; EUROPEAN PARLIAMENTS; HINGE LOSS FUNCTIONS; LARGE VOCABULARIES; LOSS FUNCTIONS; MACHINE LEARNING PROBLEMS; MAXIMUM MUTUAL INFORMATIONS; MINIMUM PHONE ERRORS; OPTIMIZATION ALGORITHMS; PLENARY SESSIONS; RECOGNITION TASKS; SUPPORT VECTORS; TRAINING ALGORITHMS; ERROR CRITERIONS; INFORMATION CRITERION; NON SMOOTHES; OVER FITTINGS;

SPEECH RECOGNITION; LEARNING ALGORITHMS;

EID: 56449091292     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (16)

1. Altun, Y., Tsochantaridis, I., & Hofmann, T. (2003), Hidden markov support vector machines. Int. Conf. on Machine Learning (ICML).
2. Eisner, J. (2001). Expectation semirings: Flexible EM for finite-state transducers. Finite-State Methods and Natural Language Processing (FSMNLP). Helsinki, Finland.
3. He, X., Deng, L., & Chou, W. (2008). Discriminative learning in sequential pattern recognition - A unifying review for optimization-oriented speech recognition. IEEE Signal Processing Magazine.
4. Heigold, G., Schlüter, R., & Ney, H. (2007). On the equivalence of Gaussian HMM and Gaussian HMM-like hidden conditional random fields. Proc. of the Int. Conf. on Spoken Language Processing (Interspeech). Antwerp, Belgium.
5. Jebara, T. (2002). Discriminative, generative, and imitative learning. Doctoral dissertation, Massachusetts Institute of Technology.
6. Li, J., Yan, Z., Lee, C., & Wang, R. (2007). A study on soft margin estimation for LVCSR. Proc. of the IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Kyoto, Japan.
7. Lööf, J., Gollan, C., Hahn, S., Heigold, G., Hoffmeister, B., Plahl, C., Rybach, D., Schlüter, R., & Ney, H. (2007). The RWTH 2007 TC-STAR evaluation system for European English and Spanish. Proc. of the Int. Conf. on Spoken Language Processing (Interspeech). Antwerp, Belgium.
8. Povey, D., Kanevsky, D., Kingsbury, B., Ramabhadran, B., Saon, G., & Visweswariah, K. (2008). Boosted MMI for model and feature-space discriminative training. Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP). Las Vegas, NV.
9. Povey, D., & Woodland, P. C. (2002). Minimum phone error and I-smoothing for improved discriminative training. Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP). Orlando, FL.
10. Sha, F., & Saul, L. (2007). Comparison of large margin training to other discriminative methods for phonetic recognition by hidden Markov models. Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP). Honolulu, Hawaii.
11. Taskar, B., Guestrin, C., & Koller, D. (2003). Max-margin markov networks. Neural Information Processing Systems Conference (NIPS).
12. Vapnik, V. (1995). The nature of statistical learning theory. Springer.
13. Weston, J., & Watkins, C. (1999). Support vector machines for multi-class pattern classification. Proc. of the Seventh European Symposium on Artificial Neural Networks.
14. Yin, Y., & Jiang, H. (2007). A fast optimization method for large margin estimation of HMMs based on second order cone programming. Proc. of the Int. Conf. on Spoken Language Processing (Interspeech). Antwerp, Belgium.
15. Yu, D., Deng, L., He, X., & Acero, A. (2007). Large-margin minimum classification error training for large-scale speech recognition tasks. Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP). Honolulu, Hawaii, USA.
16. Zhang, J., Jin, R., Yang, Y., & Hauptmann, A. (2003). Modified logistic regression: An approximation to SVM and its applications in large-scale text categorization. Int. Conference on Machine Learning (ICML).