Speech recognition technique is expected to make a great impact on many user interface areas such as toys, mobile phones, PDAs, and home appliances. Those applications basically re...
Model M, a novel class-based exponential language model, has been shown to significantly outperform word n-gram models in state-of-the-art machine translation and speech recognit...
Unrehearsed spoken language often contains disfluencies. In order to correctly interpret a spoken utterance, any such disfluencies must be identified and removed or otherwise deal...
Recently various techniques to improve the correlation model of feature vector elements in speech recognition systems have been proposed. Such techniques include semi-tied covaria...
Multilingual speech recognition obviously involves numerous research challenges, including common phoneme sets, adaptation on limited amount of training data, as well as mixed lan...