This paper presents MISTRAL, an open source statistical machine translation decoder dedicated to spoken language translation. While typical machine translation systems take a writ...
Automatic speech recognition of real-live broadcast news (BN) data (Hub-4) has become a challenging research topic in recent years. This paper summarizes our key efforts to build ...
Peter Beyerlein, Xavier L. Aubert, Reinhold Haeb-U...
This paper addresses the problem of the real-time automatic transcription of a live music performance into a symbolic format. The source data are given by any music instrument or o...
A conventional automatic speech recognizer does not perform well in the presence of noise, while human listeners are able to segregate and recognize speech in noisy conditions. We...
Yang Shao, Zhaozhang Jin, DeLiang Wang, Soundarara...
In this paper, we present a semi-supervised method for automatic speech act recognition in email and forums. The major challenge of this task is due to lack of labeled data in the...