A Logarithmic Based Pole-Zero Vocal Tract Model Estimation for Speaker Verification

EWALD ENZINGER; PETER BALAZS; DAMIÁN MARELLI; TIMO BECKER

Praga

Conferencia; IEEE Conference on on Acoustics, Speech, and Signal Processing (ICASSP); 2011

Institute of Electrical and Electronics Engineers (IEEE)

In this paper we investigate the use of formant and anti-formant measurements of nasal consonants for speaker verifi-cation. The features are obtained using a pole-zero vocal tractmodel estimate optimized by minimizing a logarithmic crite-rion which is motivated by the perception of amplitude by thehuman auditory system. A GMM-UBM approach is used forperforming speaker comparisons within the likelihood-ratioframework. Results are compared with systems based on MelFrequency Cepstral Coefficients (MFCCs) as well as formantcenter frequencies and bandwidths obtained using the SnackToolkit. The formant and anti-formant based system attainscomparable results to the MFCC system and outperforms theformant-based approach while offering a more straightfor-ward interpretation in terms of a physical speech productionmodel.