Discriminative Pronunciation Modeling Using the MPE Criterion
نویسندگان
چکیده
منابع مشابه
Discriminative Pronunciation Modeling Using the MPE Criterion
Introducing pronunciation models into decoding has been proven to be benefit to LVCSR. In this paper, a discriminative pronunciation modeling method is presented, within the framework of the Minimum Phone Error (MPE) training for HMM/GMM. In order to bring the pronunciation models into the MPE training, the auxiliary function is rewritten at word level and decomposes into two parts. One is for ...
متن کاملDiscriminative Adaptive Training Using the Mpe Criterion
This paper addresses the use of discriminative training criteria for Speaker Adaptive Training (SAT), where both the transform generation and model parameter estimation are estimated using the Minimum Phone Error (MPE) criterion. In a similar fashion to the use of I-smoothing for standard MPE training, a smoothing technique is introduced to avoid over-training when optimizing MPEbased feature-s...
متن کاملDiscriminative pronunciation modeling for dialectal speech recognition
Speech recognizers are typically trained with data from a standard dialect and do not generalize to non-standard dialects. Mismatch mainly occurs in the acoustic realization of words, which is represented by acoustic models and pronunciation lexicon. Standard techniques for addressing this mismatch are generative in nature and include acoustic model adaptation and expansion of lexicon with pron...
متن کاملDiscriminative Pronunciation Learning Using Phonetic Decoder and Minimum-classification-error Criterion
In this paper, we report our recent research aimed at improving the pronunciation-modeling component of a speech recognition system designed for mobile voice search. Our new discriminative learning technique overcomes the limitation of the traditional ways of introducing alternative pronunciations that often enlarge confusability across different lexical items. Instead, we make use of a phoneti...
متن کاملPosterior-Scaled MPE: Novel Discriminative Training Criteria
We recently discovered novel discriminative training criteria following a principled approach. In this approach training criteria are developed from error bounds on the global error for pattern classification tasks that depend on non-trivial loss functions. Automatic speech recognition (ASR) is a prominent example for such a task depending on the non-trivial Levenshtein loss. In this context, t...
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: IEICE Transactions on Information and Systems
سال: 2015
ISSN: 0916-8532,1745-1361
DOI: 10.1587/transinf.2014edl8212