The SRI March 2000 Hub-5 conversational speech transcription system (2000)
| Venue: | In Proceedings of the NIST Speech Transcription Workshop |
| Citations: | 26 - 6 self |
BibTeX
@INPROCEEDINGS{Stolcke00thesri,
author = {A. Stolcke and H. Bratt and J. Butzberger and H. Franco and V. R. Rao Gadde and M. Plauché and C. Richey and E. Shriberg and K. Sönmez and F. Weng and J. Zheng},
title = {The SRI March 2000 Hub-5 conversational speech transcription system},
booktitle = {In Proceedings of the NIST Speech Transcription Workshop},
year = {2000}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We describe SRI’s large vocabulary conversational speech recognition system as used in the March 2000 NIST Hub-5E evaluation. The system performs four recognition passes: (1) bigram recognition with phone-loop-adapted, within-word triphone acoustic models, (2) lattice generation with transcription-mode-adapted models, (3) trigram lattice recognition with adapted cross-word triphone models, and (4) N-best rescoring and reranking with various additional knowledge sources. The system incorporates two new kinds of acoustic model: triphone models conditioned on speaking rate, and an explicit joint model of within-word phone durations. We also obtained an unusually large improvement from modeling crossword pronunciation variants in “multiword ” vocabulary items. The language model (LM) was enhanced with an “anti-LM ” representing acoustically confusable word sequences. Finally, we applied a generalized ROVER algorithm to combine the N-best hypotheses from several systems based on different acoustic models. 1.
