Towards Duration Invariance of i-Vector-based Adaptive Score Normalization

It is generally conceded that duration variability has huge effects on the biometric performance of speaker recognition systems. State-of-the-art approaches, which employ ivector representations, apply adaptive symmetric (AS) scorenormalizations to improve the performance of the underlying system by using specific statistics on reference and probe templates obtained from additional datasets. The incorporation of duration information turns out to be vital in order to prevent a significant raise of entropy, since variation and likely a reduction of the signal duration from reference to probe samples is unpredictable. In this paper we propose a duration-invariant extension of the AS-Norm, which is capable of computing more robust scores over a wide range of duration variabilities. The presented technique requires less computational effort at the time of speaker verification, and yields a 19% relative-gain in the minimum detection costs on the current NIST i-vector challenge database, compared to the provided NIST i-vector baseline system.