Abstract
The Minimum Phone Error (MPE) criterion for discriminative training was shown to be able to offer acoustic models with significantly improved performance. This concept was then further extended to Feature-space Minimum Phone Error (fMPE) and offset fMPE for training feature parameters as well. This paper reviews the concept of MPE and reports the experiments and results in performing MPE, fMPE and offset fMPE on the task of Mandarin Broadcast News, and significant improvements were obtained similar to the results reported for other languages and other tasks by other sites. In addition, a new concept of dimension-weighted offset fMPE is proposed in this work and even better performance than offset fMPE was obtained.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Povey, D., Woodland, P.C.: Minimum Phone Error and I-smoothing for Improved Discriminative Training. In: Proc. ICASSP 2002 (2002)
Povey, D.: Discriminative Training for Large Vocabulary Speech Recognition, Ph.D Dissertation, Peterhouse, University of Cambridge (2004)
Povey, D., Kingsbury, B., Mangu, L., Saon, G., Soltau, H., Zweig, G.: fMPE: Discriminatively Trained Features for Speech Recognition. In: Proc. ICASSP 2005 (2005)
Povey, D.: Improvements to fMPE for Discriminative Training of Features. In: Proc. Interspeech 2005 (2005)
Kaiser, J., Horvat, B., Kacic, Z.: A Novel Loss Function for the Overall Risk Criterion Based Discriminative Training of HMM Models. In: Proc. ICSLP 2000 (2000)
Kumar, N.: Investigation of Silicon Auditory Models and Generalization of Linear Discriminant Analysis for Improved Speech Recognition, PhD Dissertation, Johns Hopkins University (1997)
Zhang, B., Matsoukas, S.: Minimum Phoneme Error Based Heteroscedastic Linear Discriminant Analysis for Speech Recognition. In: Proc. ICASSP 2005 (2005)
Gopinath, R.A.: Maximum Likelihood Modeling with Gaussian Distributions for Classification. In: Proc. ICASSP 1998 (1998)
Wang, H.-M., Chen, B., Kuo, J.-W., Cheng, S.-S.: MATBN: A Mandarin Chinese Broadcast News Corpus. International Journal of Computational Linguistics and Chinese Language Processing (2005)
Droppo, J., Acero, A.: Maximum Mutual Information SPLICE Transform for Seen and Unseen Conditions. In: Proc. Interspeech 2005 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, JY., Wan, CY., Chen, Y., Chen, B., Lee, Ls. (2006). Minimum Phone Error (MPE) Model and Feature Training on Mandarin Broadcast News Task. In: Huo, Q., Ma, B., Chng, ES., Li, H. (eds) Chinese Spoken Language Processing. ISCSLP 2006. Lecture Notes in Computer Science(), vol 4274. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11939993_31
Download citation
DOI: https://doi.org/10.1007/11939993_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-49665-6
Online ISBN: 978-3-540-49666-3
eBook Packages: Computer ScienceComputer Science (R0)