Automatic speech recognition (ASR) results contain not only ASR errors, but also disfluencies and colloquial expressions that must be corrected to create readable transcripts. We...
Graham Neubig, Yuya Akita, Shinsuke Mori, Tatsuya ...
Enriching a pronunciation dictionary with phonological variation is a challenging task, not yet solved despite several decades of research, in particular for speech-to-text transc...
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...
Ultrasound has become a useful tool for speech scientists studying mechanisms of language sound production. State-of-the-art methods for extracting tongue contours from ultrasound...
The current expansion in collections of natural language based digital documents in various media and languages is creating challenging opportunities for automatically accessing t...