Intonational speaker verification: A study on parameters and performance under noisy conditions

Prosody-based speaker verification using fundamental frequency (f
₀
) is considered. Our study consists of two phases. First, we do extensive optimization of parameters to establish a baseline system before dealing with noisy conditions. This includes a study of f
₀
extractor parameters, choice of features (discrete cosine transform, discrete Fourier transform, Legendre polynomials, linear prediction), f
₀
track interpolation (none, linear, Hermite), framing parameters and windowing (none, Hamming), f
₀
representation domain (linear, log), number of transformation coefficients and, finally, use of higher-level delta coefficients. Using the optimized parameters, we then explore the robustness of prosody features under white noise and factory noise degradations. Using a GMM-UBM system on the NIST 2006 SRE corpus, we reach an EER of 28.4 % and 27.6 % for the intonational and MFCC features respectively at -20 dB SNR white noise contamination; fusion of the two yields an EER of 24.38 %.