Wenchao Wang

Improving Short Utterance Anti-Spoofing with AASIST2

2023 · arXiv (Cornell University)

The wav2vec 2.0 and integrated spectro-temporal graph attention network (AASIST) based countermeasure achieves great performance in speech anti-spoofing. However, current spoof speech detection systems have fixed training and evaluation durations, while the performance degrades significantly …

Synthetic Speech Detection Based on Temporal Consistency and Distribution of Speaker Features

2023 · arXiv (Cornell University)

Current synthetic speech detection (SSD) methods perform well on certain datasets but still face issues of robustness and interpretability. A possible reason is that these methods do not analyze the deficiencies of synthetic speech. In …