Incorporation of Speech Duration Information in Score Fusion of Speaker Recognition Systems

TL;DR

This paper examines how speech duration affects speaker verification performance and proposes a score fusion method that improves accuracy by leveraging duration-specific information.

Contribution

It introduces a novel score fusion approach that incorporates speech duration information to enhance speaker recognition accuracy across varying durations.

Findings

Score fusion with duration info outperforms baseline methods

Performance degradation due to short speech durations is mitigated

The proposed method improves robustness in real-life scenarios

Abstract

In recent years identity-vector (i-vector) based speaker verification (SV) systems have become very successful. Nevertheless, environmental noise and speech duration variability still have a significant effect on degrading the performance of these systems. In many real-life applications, duration of recordings are very short; as a result, extracted i-vectors cannot reliably represent the attributes of the speaker. Here, we investigate the effect of speech duration on the performance of three state-of-the-art speaker recognition systems. In addition, using a variety of available score fusion methods, we investigate the effect of score fusion for those speaker verification techniques to benefit from the performance difference of different methods under different enrollment and test speech duration conditions. This technique performed significantly better than the baseline score fusion methods.