We describe a method for the fully automatic learning of hierarchical finite state translation models. The input to the method is transcribed speech utterances and their correspon...
With the development of speech and language processing, speech translation systems have been developed. These studies target spoken dialogues, and employ consecutive interpretatio...
Relationships that link static documents discussed during meetings to the corresponding speech transcripts can be of various kinds. The most important ones, thematic links, quotat...
In this paper, we compare and combine different approaches for instrumentally predicting the perceived quality of Text-to-Speech systems. First, a log-likelihood is determined by ...
Hindi and Urdu share a common phonology, morphology and grammar but are written in different scripts. In addition, the vocabularies have also diverged significantly especially in ...