Minimum hypothesis phone error as a decoding method for speech recognition
Haihua Xu, Daniel Povey, Jie Zhu, Guanyong Wu · 2009
In this paper we show how methods for approximating phone error as normally used for Minimum Phone Error (MPE) dis-criminative training, can be used instead as a decoding criterion for lattice rescoring. This is an alternative to Confusion Net-works (CN) which are commonly used in speech recognition. The standard (Maximum A Posteriori) decoding approach is a Minimum Bayes Risk estimate with respect to the Sentence Er-ror Rate (SER); however, we are typically more interested in the Word Error Rate (WER). Methods such as CN and our pro-posed Minimum Hypothesis Phone Error (MHPE) aim to get closer to minimizing the expected WER. Based on preliminary experiments we find that our approach gives more improvement than CN, and is conceptually simpler.