ROVER [1] and its successor voting procedures have been shown to be quite effective in reducing the recognition word error rate (WER). The success of these methods has been attributed to their minimum Bayes-risk (MBR) nature: they produce the hypothesis with the least expected word error. In this paper we develop a general procedure within the MBR framework, called segmental MBR recognition, that encompasses current voting techniques and allows further extensions that yield lower expected WER. It also allows incorporation of loss functions other than the WER. We present a derivation of voting procedure of N-best ROVER as an instance of segmental MBR recognition. We then present an extension, called e-ROVER, that alleviates some of the restrictions of N-best ROVER by better approximating the WER. e-ROVER is compared with N-best ROVER on multi-lingual acoustic modeling task and is shown to yield modest yet significant and easily obtained improvements.
J. Fiscus. A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER). IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 347-354, Santa Barbara, CA, 1997.
Cite as: Goel, V., Kumar, S., Byrne, W. (2000) Segmental minimum Bayes-risk ASR voting strategies. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 3, 139-142, doi: 10.21437/ICSLP.2000-497
@inproceedings{goel00_icslp,
author={Vaibhava Goel and Shankar Kumar and William Byrne},
title={{Segmental minimum Bayes-risk ASR voting strategies}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 3, 139-142},
doi={10.21437/ICSLP.2000-497}
}