collaborators

5 papers

cs.SD2024

WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification

Junzuo Zhou, Jiangyan Yi, Yong Ren +3

Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before co…

eess.AS2024

ADD 2023: Towards Audio Deepfake Detection and Analysis in the Wild

Jiangyan Yi, Chu Yuan Zhang, Jianhua Tao +5

The growing prominence of the field of audio deepfake detection is driven by its wide range of applications, notably in protecting the public from potential fraud and other malicio…

cs.SD2024

Reject Threshold Adaptation for Open-Set Model Attribution of Deepfake Audio

Xinrui Yan, Jiangyan Yi, Jianhua Tao +6

Open environment oriented open set model attribution of deepfake audio is an emerging research topic, aiming to identify the generation models of deepfake audio. Most previous work…

cs.SD2024

Audio Deepfake Attribution: An Initial Dataset and Investigation

Xinrui Yan, Jiangyan Yi, Jianhua Tao +1

The rapid progress of deep speech synthesis models has posed significant threats to society such as malicious manipulation of content. This has led to an increase in studies aimed…

cs.SD2024

TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking

Junzuo Zhou, Jiangyan Yi, Tao Wang +5

Various threats posed by the progress in text-to-speech (TTS) have prompted the need to reliably trace synthesized speech. However, contemporary approaches to this task involve add…