Although the performance of state-of-the-art automatic speech recognition systems on the challenging task of broadcast news transcription has improved considerably in recent years, many of the systems operate in 130-300 times real-time. Many applications of automatic transcription of broadcast news, eg. closed-caption subtitles for television broadcasts, require real-time operation. This paper describes a connectionist-HMM system for broadcast news transcription, and the modifications to this system necessary for real-time operation. We show that real-time operation is possible with a relative increase in word error rate of about 12%.
Cite as: Cook, G., Robinson, T., Christie, J. (1998) Real-time recognition of broadcast news. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0065, doi: 10.21437/ICSLP.1998-614
@inproceedings{cook98_icslp,
author={Gary Cook and Tony Robinson and James Christie},
title={{Real-time recognition of broadcast news}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0065},
doi={10.21437/ICSLP.1998-614}
}