This paper presents a method for rescoring the speech recognition lattices on-the-fly to increase the word accuracy while preserving low latency of a real-time speech recognition ...
Duration of phonemic segments provide important cues for distinguishing words in languages such as Arabic. Recently, we proposed a discriminatively estimated joint acoustic, durat...
Abstract. In automatic sign language translation, one of the main problems is the usage of spatial information in sign language and its proper representation and translation, e.g. ...
Hitherto, one major challenge to sign language recognition is how to develop approaches that scale well with increasing vocabulary size. In large vocabulary speech recognition real...
This paper describes our participation in the TREC-9 Spoken Document Retrieval (SDR) track. The THISL SDR system consists of a realtime version of a hybrid connectionist/HMM large...