Auditory signal processing as a basis for speaker recognition

We exploit models of auditory signal processing at different levels along the auditory pathway for use in speaker recognition. A low-level nonlinear model, at the cochlea, provides accentuated signal dynamics, while a high-level model, at the inferior colliculus, provides frequency analysis of modulation components that reveals an additional temporal structure. A variety of features are derived from the low-level dynamic and high-level modulation signals. Fusion of likelihood scores from feature sets at different auditory levels with scores from standard Mel-cepstral features provides an encouraging speaker recognition performance gain over use of the Mel-cepstrum alone with corpora from land-line and cellular telephone communications.