We focus in this paper on the named entity recognition task in spoken data. The proposed approach investigates the use of various contexts of the words to improve recognition. Exp...
Grounded language models represent the relationship between words and the non-linguistic context in which they are said. This paper describes how they are learned from large corpo...
Update of acoustic and language models is vital to maintain performance of automatic speech recognition (ASR) systems. To alleviate efforts for updating models, we propose a "...
Yuya Akita, Masato Mimura, Graham Neubig, Tatsuya ...
This paper presents an interactive visualisation system that assists users of semi-automatic speech transcription systems to assess alternative recognition results in real time an...
Saturnino Luz, Masood Masoodian, Bill Rogers, Bo Z...
This paper explores the problem of identifying sentence boundaries in the transcriptions produced by automatic speech recognition systems. An experiment which determines the level...