The SYSU System for the Interspeech 2015 Automatic Speaker Verification Spoofing and Countermeasures Challenge

TL;DR

This paper presents a multi-feature fusion system using i-vector subsystems and classifiers to detect spoofed speech in speaker verification, achieving very low error rates on the INTERSPEECH 2015 challenge dataset.

Contribution

It introduces a novel fusion approach combining acoustic, phase, and phonetic features with multiple classifiers for improved spoofing detection.

Findings

Achieved 0.29% EER on development set

Achieved 3.26% EER on test set

Enhanced performance through feature and score fusion

Abstract

Many existing speaker verification systems are reported to be vulnerable against different spoofing attacks, for example speaker-adapted speech synthesis, voice conversion, play back, etc. In order to detect these spoofed speech signals as a countermeasure, we propose a score level fusion approach with several different i-vector subsystems. We show that the acoustic level Mel-frequency cepstral coefficients (MFCC) features, the phase level modified group delay cepstral coefficients (MGDCC) and the phonetic level phoneme posterior probability (PPP) tandem features are effective for the countermeasure. Furthermore, feature level fusion of these features before i-vector modeling also enhance the performance. A polynomial kernel support vector machine is adopted as the supervised classifier. In order to enhance the generalizability of the countermeasure, we also adopted the cosine similarity and PLDA scoring as one-class classifications methods. By combining the proposed i-vector subsystems with the OpenSMILE baseline which covers the acoustic and prosodic information further improves the final performance. The proposed fusion system achieves 0.29% and 3.26% EER on the development and test set of the database provided by the INTERSPEECH 2015 automatic speaker verification spoofing and countermeasures challenge.