Audio deepfake detection is an emerging active topic. A growing number of literatures have
aimed to study deepfake detection algorithms and achieved effective performance, the …

ASVspoof 2021 is the forth edition in the series of biannual challenges which aim to promote
the study of spoofing and the design of countermeasures to protect automatic speaker …

Artefacts that differentiate spoofed from bona-fide utterances can reside in specific temporal
or spectral intervals. Their reliable detection usually depends upon computationally …

Benchmarking initiatives support the meaningful comparison of competing solutions to
prominent problems in speech and language processing. Successive benchmarking …

A great deal of recent research effort on speech spoofing countermeasures has been
invested into back-end neural networks and training criteria. We contribute to this effort with …

Artefacts that serve to distinguish bona fide speech from spoofed or deepfake speech are
known to reside in specific subbands and temporal segments. Various approaches can be …

Current text-to-speech algorithms produce realistic fakes of human voices, making deepfake
detection a much-needed area of research. While researchers have presented various …

The constant Q transform (CQT) has been shown to be one of the most effective speech
signal pre-transforms to facilitate synthetic speech detection, followed by either hand-crafted …

Self-supervised speech model is a rapid progressing research topic, and many pre-trained
models have been released and used in various down stream tasks. For speech anti …

In the rapidly evolving digital landscape, the generation of fake visual, audio, and textual
content poses a significant threat to the trust of society, political stability, and integrity of …