Engine-Independent ASR Error Management for Dialog Systems

Abstract

This paper describes a method of ASR (automatic speech rec ognition) engine independent error correction for a dialog system. The proposed method can correct ASR errors only with a text corpus which is used for training of the target dialog system, and it means that the method is independent of the ASR engine. We evaluated our method on two test corpora (Korean and English) that are parallel corpora including ASR results and their correct transcriptions. Overall results indi-cate that the method decreases the word error rate of the ASR results and recovers the errors in the important attributes of the dialog system. The method is general and can also be applied to the other speech based applications such as voice ques-tion-answering and speech information extraction systems.