Title :
Speech denoising based on an auditory filterbank
Author :
Lin, L. ; Ambikairajah, E.
Author_Institution :
Sch. of Electr. Eng. & Telecommun., New South Wales Univ., Sydney, NSW, Australia
Abstract :
We propose a speech denoising technique based on an auditory filter bank in the equivalent rectangular bandwidth scale. The denoising is realized simply by scaling the output of each auditory filter by a factor calculated from the updated signal statistics in each channel. The performance of the algorithm is assessed in white and coloured noise. The proposed method gives improved speech quality and a very low level of musical noise. The algorithm is very effective in reducing additive coloured noise due to its sub-band nature. The proposed technique also has potential application in robust speech recognition using an auditory filter bank as a front end.
Keywords :
acoustic noise; audio signal processing; channel bank filters; signal denoising; speech processing; speech recognition; statistical analysis; white noise; additive coloured noise; auditory filterbank; equivalent rectangular bandwidth scale; musical noise; robust speech recognition; signal statistics; speech denoising; white noise; Additive noise; Bandwidth; Channel bank filters; Colored noise; Filter bank; Noise level; Noise reduction; Noise robustness; Speech enhancement; Statistics;
Conference_Titel :
Signal Processing, 2002 6th International Conference on
Print_ISBN :
0-7803-7488-6
DOI :
10.1109/ICOSP.2002.1181115