Spoofing detection under noisy conditions: a preliminary investigation and an initial database
This addresses the problem of spoofing detection in real-life noisy environments for ASV systems, but it is incremental as it builds on existing databases and methods.
The authors tackled spoofing detection for automatic speaker verification under noisy conditions, finding that system performance degrades significantly when using models trained on clean data, with phase-based features showing more noise robustness than magnitude-based ones.
Spoofing detection for automatic speaker verification (ASV), which is to discriminate between live speech and attacks, has received increasing attentions recently. However, all the previous studies have been done on the clean data without significant additive noise. To simulate the real-life scenarios, we perform a preliminary investigation of spoofing detection under additive noisy conditions, and also describe an initial database for this task. The noisy database is based on the ASVspoof challenge 2015 database and generated by artificially adding background noises at different signal-to-noise ratios (SNRs). Five different additive noises are included. Our preliminary results show that using the model trained from clean data, the system performance degrades significantly in noisy conditions. Phase-based feature is more noise robust than magnitude-based features. And the systems perform significantly differ under different noise scenarios.