Adaptive Training for Large Vocabulary Continuous Speech Recognition (2006)
Cached
Download Links
| Citations: | 8 - 2 self |
BibTeX
@MISC{Yu06adaptivetraining,
author = {Kai Yu},
title = {Adaptive Training for Large Vocabulary Continuous Speech Recognition},
year = {2006}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Summary In recent years, there has been a trend towards training large vocabulary continuous speech recognition (LVCSR) systems on a large amount of found data. Found data is recorded from spontaneous speech without careful control of the recording acoustic conditions, for example, conversational telephone speech. Hence, it typically has greater variability in terms of speaker and acoustic conditions than specially collected data. Thus, in addition to the desired speech variability required to discriminate between words, it also includes various non-speech variabil-ities, for example, the change of speakers or acoustic environments. The standard approach to handle this type of data is to train hidden Markov models (HMMs) on the whole data set as if all data comes from a single acoustic condition. This is referred to as multi-style training, for exam-ple speaker-independent training. Effectively, the non-speech variabilities are ignored. Though good performance has been obtained with multi-style systems, these systems account for all variabilities. Improvement may be obtained if the two types of variabilities in the found data are modelled separately. Adaptive training has been proposed for this purpose. In contrast to multi-style training, a set of transforms is used to represent the non-speech variabilities. A canonical
Keyphrases
adaptive training large vocabulary continuous speech recognition found data non-speech variability acoustic condition multi-style training exam-ple speaker-independent training good performance recent year standard approach conversational telephone speech various non-speech variabil-ities multi-style system spontaneous speech careful control large amount hidden markov model speech variability single acoustic condition acoustic environment whole data set
