The IBM 2004 Conversational Telephony System for Rich Transcription

Hagen Soltau, Brian Kingsbury, Lidia Mangu, Daniel Povey, George Saon, Geoffrey ZweigICASSP 2005 · OpenReview

Abstract

This paper describes the technical advances in IBM's conversational telephony submission to the DARPA-sponsored 2004 rich transcription evaluation (RT-04). These advances include a system architecture based on cross-adaptation; a new form of feature-based MPE training; the use of a full-scale discriminatively trained full covariance Gaussian system; the use of septaphone cross-word acoustic context in static decoding graphs; and the incorporation of 2100 hours of training data in every system component. These advances reduced the error rate by approximately 21% relative, on the 2003 test set, over the best-performing system in last year's evaluation, and produced the best results on the RT-04 current and progress CTS data.
BibTeX
@inproceedings{soltau2005ibm,
  author = {Hagen Soltau and Brian Kingsbury and Lidia Mangu and Daniel Povey and George Saon and Geoffrey Zweig},
  title = {{The IBM 2004 Conversational Telephony System for Rich Transcription}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2005},
  url = {https://openreview.net/forum?id=H9UoD-CRLxc},
}

Loading related content...

Figure