7 papers
Investigating Codec-Internal Latent Audio Watermarking for Neural Codec Robustness
Zi Hu, Houmin Sun, Linxi Li +4
Neural audio codecs are challenging transformations for audio watermarking because they re-encode, quantize, and resynthesize speech. This paper investigates continuous latent-spac…
SynSFX: Multi-Model Sound Effects Synthesis Dataset for Deepfake Detection and Evaluation
Linxi Li, Yuncong Yu, Qianwei Guo +3
While audio deepfake detection has advanced significantly, representative detectors show limited generalization to synthetic sound effects. Existing environmental audio datasets su…
USV: Towards Understanding the User-generated Short-form Videos
Haoyue Cheng, Su Xu, Liwei Jin +3
Several large-scale video datasets have been published these years and have advanced the area of video understanding. However, the newly emerged user-generated short-form videos ha…
Making Separation-First Multi-Stream Audio Watermarking Feasible via Joint Training
Houmin Sun, Zi Hu, Linxi Li +4
Modern audio is created by mixing stems from different sources, raising the question: can we independently watermark each stem and recover all watermarks after separation? We study…
MultiAPI Spoof: A Multi-API Dataset and Local-Attention Network for Speech Anti-spoofing Detection
Xueping Zhang, Zhenshan Zhang, Yechen Wang +3
Existing speech anti-spoofing benchmarks rely on a narrow set of public models, creating a substantial gap from real-world scenarios in which commercial systems employ diverse, oft…
The Impact of Audio Watermarking on Audio Anti-Spoofing Countermeasures
Zhenshan Zhang, Xueping Zhang, Yechen Wang +2
This paper presents the first study on the impact of audio watermarking on spoofing countermeasures. While anti-spoofing systems are essential for securing speech-based application…
CompSpoof: A Dataset and Joint Learning Framework for Component-Level Audio Anti-spoofing Countermeasures
Xueping Zhang, Yechen Wang, Linxi Li +2
Component-level audio Spoofing (Comp-Spoof) targets a new form of audio manipulation where only specific components of a signal, such as speech or environmental sound, are forged o…