DocumentCode :
2163284
Title :
Efficient real-time noise estimation without explicit speech, non-speech detection: an assessment on the AURORA corpus
Author :
Evans, Nicholas W D ; Mason, John S. ; Fauve, Benoit
Author_Institution :
Dept. of Electron. & Electr. Eng., Univ. of Wales, Swansea, UK
Volume :
2
fYear :
2002
fDate :
2002
Firstpage :
985
Abstract :
This paper addresses the problem of noise estimation for speech enhancement and automatic speech recognition. In the context of mobile telephony, there is a requirement for low resource algorithms which must run at real-time. This paper describes the implementation of a previously published approach, termed quantile-based noise estimation, integrated within a conventional spectral subtraction framework. The novelty lies in the efficiency of the noise estimation process. Assessment is carried out on the AURORA corpus and demonstrates significant improvements in efficiency. Automatic speech recognition results show an average relative improvement of 26% over the baseline.
Keywords :
mobile radio; noise; radiotelephony; spectral analysis; speech enhancement; speech recognition; AURORA corpus; automatic speech recognition; efficient real-time noise estimation; low resource algorithms; mobile telephony; noise estimation efficiency; quantile-based noise estimation; spectral subtraction; speech enhancement; Additive noise; Automatic speech recognition; Background noise; Network servers; Noise robustness; Proposals; Speech enhancement; Speech recognition; Telecommunication traffic; Telephony;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Digital Signal Processing, 2002. DSP 2002. 2002 14th International Conference on
Print_ISBN :
0-7803-7503-3
Type :
conf
DOI :
10.1109/ICDSP.2002.1028255
Filename :
1028255
Link To Document :
بازگشت