Recent Developments in Large Vocabulary Continuous Speech Recognition

Abstract

This paper overviews a series of recent approaches to front-end processing, acoustic modeling, language modeling, and back-end search and system combination which have made contributions for large vocabulary continuous speech recognition (LVCSR) systems. These approaches include the feature transformations, speaker-adaptive features, and discriminative features in front-end processing, the feature-space and model-space discriminative training, deep neural networks, and speaker adaptation in acoustic modeling, the backoff smoothing, large-span modeling, and model regularization in language modeling, and the system combination, cross-adaptation, and boosting in search and system combination. Some future directions for LVCSR research are also addressed.