| Title | Comparing spectrum estimators in speaker verification under additive noise degradation |
| Authors | C. Hanilci, T. Kinnunen, R. Saeidi, J. Pohjalainen, P. Alku, F. Ertas, J. Sandberg, Maria Sandsten |
| Alternative Location | http://ieeexplore.ieee.org/..., Restricted Access |
| Alternative Location | http://dx.doi.org/10.1109/I..., Restricted Access |
| Publication | Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on |
| Year | 2012 |
| Pages | 4769 - 4772 |
| Document type | Conference paper |
| Conference name | 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
| Conference Date | 2012-03-25/2012-03-30 |
| Conference Location | Kyoto, Japan |
| Status | Published |
| Quality controlled | Yes |
| Language | eng |
| Publisher | IEEE |
| Abstract English | Different short-term spectrum estimators for speaker verification under additive noise are considered. Conventionally, mel-frequency cepstral coefficients (MFCCs) are computed from discrete Fourier transform (DFT) spectra of windowed speech frames. Recently, linear prediction (LP) and its temporally weighted variants have been substituted as the spectrum analysis method in speech and speaker recognition. In this paper, 12 different short-term spectrum estimation methods are compared for speaker verification under additive noise contamination. Experimental results conducted on NIST 2002 SRE show that the spectrum estimation method has a large effect on recognition performance and stabilized weighted LP (SWLP) and minimum variance distortionless response (MVDR) methods yield approximately 7 % and 8 % relative improvements over the standard DFT method at -10 dB SNR level of factory and babble noises, respectively in terms of equal error rate (EER). |
| Keywords | speaker verification, spectrum estimation, |
| ISBN/ISSN/Other | ISSN: 1520-6149 (online) ISBN: 978-1-4673-0045-2 (print) |
Questions: webmaster
Last update: 2013-04-11
Centre for Mathematical Sciences, Box 118, SE-22100, Lund. Telefon: +46 46-222 00 00 (vx)