Comparing spectrum estimators in speaker verification under additive noise degradation
Date
2012
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Abstract
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).
Description
Bu çalışma, 25-30 Mart 2012 tarihleri arasında Kyoto[Japonya]’da düzenlenen IEEE International Conference on Acoustics, Speech and Signal Processing’da bildiri olarak sunulmuştur.
Keywords
Acoustics, Engineering, Spectrum estimation, Speaker verification, Weighted linear prediction, Speech, Recognition, Acoustic noise, Additive noise, Discrete, Signal processing, Spectrum analysis, Babble noise, Dft method, Equal error rate, Linear prediction, Mel-frequency cepstral coefficients, Minimum variance distortionless response, Noise contamination, Noise degradations, Recognition performance, Speaker recognition, Fourier transforms, Spectrum estimators, Speech frames, Speech recognition
Citation
Hanilci, C. vd. (2012). "Comparing spectrum estimators in speaker verification under additive noise degradation". International Conference on Acoustics Speech and Signal Processing ICASSP, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4769-4772.