DocumentCode :
2932834
Title :
An efficient multistage Rover method for Automatic Speech recognition
Author :
Haihua Xu ; Jie Zhu ; Wu, Guanyong
Author_Institution :
Dept. of Electron. Eng., Shanghai Jiao Tong Univ., Shanghai, China
fYear :
2009
fDate :
June 28 2009-July 3 2009
Firstpage :
894
Lastpage :
897
Abstract :
In this paper, we implemented a multistage recognizer output voting error reduction (ROVER) method for better automatic speech recognition (ASR). The first stage ROVER is conducted by combining three recognizers, which are respectively trained with maximum likelihood estimation (MLE), minimum phone error (MPE) and recently proposed boosted maximum mutual information (BMMI) criteria. After that the second stage ROVER is performed on two groups of recognizers, which are separately adapted with maximum a posteriori (MAP) and maximum likelihood linear regression (MLLR) methods based on results from the first stage ROVER. It is found MAP adapted recognizers based ROVER does not lead to word error rate (WER) reduction while MLLR adapted recognizers based ROVER is still effective on recognition accuracy improvement. Finally, the third stage ROVER is constructed by combining adapted and unadapted recognizers, and the best WER is obtained by combining MLLR adapted recognizers with BMMI trained recognizers that are not adapted, which achieved 6.0% and 3.0% relative WER reduction, as opposed to the best result from the one-best decoding method and the single stage ROVER method accordingly.
Keywords :
maximum likelihood estimation; regression analysis; speech recognition; automatic speech recognition; boosted maximum mutual information criteria; decoding method; maximum a posteriori method; maximum likelihood estimation; maximum likelihood linear regression method; minimum phone error; multistage Rover method; multistage recognizer output voting error reduction; word error rate reduction; Adaptation model; Automatic speech recognition; Decision trees; Electronic voting; Error analysis; Error correction; Maximum likelihood decoding; Maximum likelihood estimation; Maximum likelihood linear regression; Mutual information; ASR; ROVER; unsupervised model adaptation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on
Conference_Location :
New York, NY
ISSN :
1945-7871
Print_ISBN :
978-1-4244-4290-4
Electronic_ISBN :
1945-7871
Type :
conf
DOI :
10.1109/ICME.2009.5202639
Filename :
5202639
Link To Document :
بازگشت