Minimum Bayes Risk decoding and system combination based on a recursion for edit distance

作者：Xu, Haihua; Povey, Daniel^*; Mangu, Lidia; Zhu, Jie

来源：Computer Speech and Language, 2011, 25(4): 802-828.

DOI：10.1016/j.csl.2011.03.001

• Speech recognition
• Minimum Bayes Risk decoding

In this paper we describe a method that can be used for Minimum Bayes Risk (MBR) decoding for speech recognition. Our algorithm can take as input either a single lattice, or multiple lattices for system combination. It has similar functionality to the widely used Consensus method, but has a clearer theoretical basis and appears to give better results both for MBR decoding and system combination. Many different approximations have been described to solve the M BR decoding problem, which is very difficult from an optimization point of view. Our proposed method solves the problem through a novel forward backward recursion on the lattice, not requiring time markings. We prove that our algorithm iteratively improves a bound on the Bayes risk.

• 出版日期2011-10
• 单位IBM; Microsoft; 上海交通大学