IBM Watson is proud to announce a major advance in the transcription of conversational speech. We built a system capable of very low error rates on a popular scientific benchmark that consists of telephone conversations – the NIST Switchboard corpus (“EvalSet-2″). Furthermore, this was achieved by using only publicly available data (details available on request) to train the underlying models. The performance of our new system – an 8% word error rate – is 36% better than previously reported external results.
- IBM Watson Announcement
- IBM Watson Announcement
No comments:
Post a Comment