DocumentCode :
2787978
Title :
Nonlinear filtering of spectrotemporal modulations in speech enhancement
Author :
Mirbagheri, Majid ; Mesgarani, Nima ; Shamma, Shihab
Author_Institution :
Electr. & Comput. Eng. Dept., Univ. of Maryland, College Park, MD, USA
fYear :
2010
fDate :
14-19 March 2010
Firstpage :
5478
Lastpage :
5481
Abstract :
A monaural noise-suppression algorithm is proposed that nonlinearly manipulates the spectrotemporal modulations of speech as represented in a model of auditory cortical processing. A distinctive aspect of this approach is its consideration of the non-stationary dynamic behavior of speech that is captured using nonlinear filters, thus achieving excellent perceptual quality in the presence of many types of additive noise. Subjective tests demonstrate a significant improvement in the quality of the enhanced speech over the noisy samples even at SNRs as low as -5 dB.
Keywords :
nonlinear filters; speech enhancement; auditory cortical processing; monaural noise-suppression algorithm; nonlinear filtering; nonstationary dynamic speech behavior; perceptual speech quality; spectrotemporal modulations; speech enhancement; Acoustic noise; Filtering; Frequency estimation; Nonlinear filters; Psychoacoustic models; Psychology; Spectrogram; Speech enhancement; Speech processing; Working environment noise; cortical processing; noise suppression; nonlinear filters; spectrotemporal modulations; speech enhancement;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on
Conference_Location :
Dallas, TX
ISSN :
1520-6149
Print_ISBN :
978-1-4244-4295-9
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2010.5494912
Filename :
5494912
Link To Document :
بازگشت