Articulation rate filtering of CQCC features for automatic speaker verification

This paper introduces a new articulation rate filter and reports its combination with recently proposed constant Q cepstral coefficients (CQCCs) in their first application to automatic speaker verification (ASV). CQCC features are extracted with the constant Q transform (CQT), a perceptually-inspired alternative to Fourier-based approaches to time-frequency analysis. The CQT offers greater frequency resolution at lower frequencies and greater time resolution at higher frequencies. When coupled with cepstral analysis and the new articulation rate filter, the resulting CQCC features are readily modelled using conventional techniques. A comparative assessment of CQCCs and mel frequency cepstral coefficients (MFCC) for a short-duration speaker verification scenario shows that CQCCs generally outperform MFCCs and that the two feature representations are highly complementary; fusion experiments with the RSR2015 and RedDots databases show relative reductions in equal error rates of as much as 60% compared to an MFCC baseline.