Minimum phone error training of precision matrix models
نویسندگان
چکیده
منابع مشابه
Discriminative pronunciation modeling based on minimum phone error training
Introducing pronunciation models into decoding has proven beneficial for LVCSR. As Minimum Phone Error (MPE) training has almost become a standard scheme for acoustic modeling, a discriminative pronunciation modeling method is investigated under the framework of MPE training. In order to bring the pronunciation models into MPE training, the auxiliary function of MPE training is rewritten at wor...
متن کاملMinimum phone error discriminative training for Mandarin Chinese speaker adaptation
Speaker adaptation is an efficient way to model a new speaker from an existing speaker-independent model with limited speaker-dependent data. In this paper, we investigate the use of discriminative training schemes based on the minimum phone error (MPE) criterion to improve a well-known speaker adaptation technique, a combination of transform-based adaptation and Bayesian adaptation. Furthermor...
متن کاملOn the Use of Frame-level Information Cues for Minimum Phone Error Training of Acoustic Models
This paper considers discriminative training of acoustic models for Mandarin large vocabulary continuous speech recognition. Two frame-level information cues were explored and integrated into the minimum phone error (MPE) training. First, the frame-level entropy of Gaussian posterior probabilities obtained from the word lattice of the training utterance was exploited to weight the framelevel st...
متن کاملComplementary Phone Error Training
This paper introduces a novel method for the training of a complementary acoustic model with respect to set of given acoustic models. The method is based upon an extension of the Minimum Phone Error (MPE) criterion and aims at producing a model that makes complementary phone errors to those already trained. The technique is therefore called Complementary Phone Error (CPE) training. The method i...
متن کاملMinimum error training of log-linear translation models
Recent work on training of log-linear interpolation models for statistical machine translation reported performance improvements by optimizing parameters with respect to translation quality, rather than to likelihood oriented criteria. This work presents an alternative and more direct training procedure for log-linear interpolation models. In addition, we point out the subtle interaction betwee...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Audio, Speech and Language Processing
سال: 2006
ISSN: 1558-7916
DOI: 10.1109/tsa.2005.858062