DocumentCode :
3161774
Title :
The linear prediction inverse modulation transfer function (LP-IMTF) filter for spectral enhancement, with applications to speaker recognition
Author :
Borgström, Bengt J. ; McCree, Alan
Author_Institution :
MIT Lincoln Lab., Lexington, MA, USA
fYear :
2012
fDate :
25-30 March 2012
Firstpage :
4065
Lastpage :
4068
Abstract :
We propose a method for spectral enhancement of reverberant speech based on inverting the modulation transfer function (MTF). Using all-pole models of modulation spectra allows the linear prediction inverse MTF (LP-IMTF) filter to exhibit a smooth frequency response, and allows it to be implemented as a low-order IIR filter in the modulation envelope domain. The proposed filter adapts to current acoustic conditions without relying on explicit information regarding reverberation time. Additionally, the LP-IMTF framework allows for estimation of useful side information, such as local signal-to-reverberation ratios and band-specific reverberation times. As example applications, the LP-IMTF system is applied to enhancement and speaker recognition of reverberant speech, and significant performance improvements are achieved.
Keywords :
IIR filters; frequency response; optical transfer function; speaker recognition; LP-IMTF filter; MTF; acoustic conditions; band-specific reverberation times; frequency response; linear prediction inverse modulation transfer function filter; local signal-to-reverberation ratios; low-order IIR filter; modulation envelope domain; modulation spectra all-pole models; reverberant speech; speaker recognition; spectral enhancement; Modulation; Reverberation; Speaker recognition; Speech; Speech enhancement; Speech recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
ISSN :
1520-6149
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2012.6288811
Filename :
6288811
Link To Document :
بازگشت