COMPARING SPECTRUM ESTIMATORS IN SPEAKER VERIFICATION UNDER ADDITIVE NOISE DEGRADATION

Hanilci C., Kinnunen T., Saeidi R., Pohjalainen J., Alku P., Ertas F., ...Daha Fazla

IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, Japonya, 25 - 30 Mart 2012, ss.4769-4772 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Doi Numarası: 10.1109/icassp.2012.6288985
  • Basıldığı Şehir: Kyoto
  • Basıldığı Ülke: Japonya
  • Sayfa Sayıları: ss.4769-4772
  • Bursa Uludağ Üniversitesi Adresli: Evet

Özet

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).