The 2004 BBN/LIMSI 20xRT English conversational telephone speech recognition system

Rohit Prasad, Spyros Matsoukas, C.-L. Kao, Jeff Z. Ma, D.-X. Xu, T. Colthurst, O. Kimball, Richard Schwartz, Jean-Luc Gauvain, Lori Lamel, Holger Schwenk, G. Adda, F. Lefevre

In this paper we describe the English Conversational Telephone Speech (CTS) recognition system jointly developed by BBN and LIMSI under the DARPA EARS program for the 2004 evaluation conducted by NIST. The 2004 BBN/LIMSI system achieved a word error rate (WER) of 13.5% at 18.3xRT (real-time as measured on Pentium 4 Xeon 3.4 GHz Processor) on the EARS progress test set. This translates into a 22.8% relative improvement in WER over the 2003 BBN/LIMSI EARS evaluation system, which was run without any time constraints. In addition to reporting on the system architecture and the evaluation results, we also highlight the significant improvements made at both sites.

doi: 10.21437/Interspeech.2005-539

Cite as: Prasad, R., Matsoukas, S., Kao, C.-L., Ma, J.Z., Xu, D.-X., Colthurst, T., Kimball, O., Schwartz, R., Gauvain, J.-L., Lamel, L., Schwenk, H., Adda, G., Lefevre, F. (2005) The 2004 BBN/LIMSI 20xRT English conversational telephone speech recognition system. Proc. Interspeech 2005, 1645-1648, doi: 10.21437/Interspeech.2005-539

@inproceedings{prasad05b_interspeech,
  author={Rohit Prasad and Spyros Matsoukas and C.-L. Kao and Jeff Z. Ma and D.-X. Xu and T. Colthurst and O. Kimball and Richard Schwartz and Jean-Luc Gauvain and Lori Lamel and Holger Schwenk and G. Adda and F. Lefevre},
  title={{The 2004 BBN/LIMSI 20xRT English conversational telephone speech recognition system}},
  year=2005,
  booktitle={Proc. Interspeech 2005},
  pages={1645--1648},
  doi={10.21437/Interspeech.2005-539}
}