Abstract. In recent years, there has been a great deal of work in modeling audio using non-negative matrix factorization and its probabilistic counterparts as they yield rich model...
We explore morphology-based and sub-word language modeling approaches proposed for morphologically rich languages, and evaluate and contrast them for Turkish broadcast news transc...
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 ...
The success of spoken dialog applications depends strongly on the quality of the semantic confidence measure that determines the selection of the dialog strategy. However, the sem...