Second order vector taylor series based robust speech recognition

Author

Suliang Bu ; Yanmin Qian ; Khe Chai Sim ; Yongbin You ; Kai Yu

Author_Institution

Dept. of Comput. Sci. & Eng., Shanghai Jiao Tong Univ., Shanghai, China

fYear

2014

fDate

4-9 May 2014

Firstpage

1769

Lastpage

1773

Abstract

Vector Taylor Series (VTS) model based compensation approach has been successfully applied to various robust speech recognition tasks. In this paper, a novel method to derive the formula to calculate the static and dynamic statistics based on second-order VTS (sVTS) is presented, which provides a new insight on the VTS approximation. Lengthy derivation could therefore be avoided when high order VTS is used and the proposed approach is more compact and easier to implement compared to previous high order VTS approaches. Experiments on Aurora 4 showed that the proposed sVTS based model compensation approach obtained 16.7% relative WER reduction over traditional first-order VTS (fVTS) approach.

Keywords

approximation theory; compensation; speech recognition; statistical analysis; Aurora 4; VTS approximation; compensation approach; dynamic statistics; relative WER reduction; robust speech recognition; second order vector Taylor series; static statistics; Approximation methods; Noise; Noise measurement; Speech; Speech recognition; Taylor series; Vectors; Vector Taylor Series; model based compensation; robust speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on

Conference_Location

Florence

Type

conf

DOI

10.1109/ICASSP.2014.6853902

Filename

6853902