SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan

TL;DR

The paper introduces the SVDD Challenge 2024, aiming to advance detection of AI-generated singing voice deepfakes amidst unique challenges posed by musical and background elements.

Contribution

It presents the first dedicated challenge for singing voice deepfake detection, encouraging focused research in this specialized area.

Findings

Establishment of a new benchmark for SVDD

Promotion of research through a dedicated challenge

Preparation for evaluation at SLT 2024

Abstract

The rapid advancement of AI-generated singing voices, which now closely mimic natural human singing and align seamlessly with musical scores, has led to heightened concerns for artists and the music industry. Unlike spoken voice, singing voice presents unique challenges due to its musical nature and the presence of strong background music, making singing voice deepfake detection (SVDD) a specialized field requiring focused attention. To promote SVDD research, we recently proposed the "SVDD Challenge," the very first research challenge focusing on SVDD for lab-controlled and in-the-wild bonafide and deepfake singing voice recordings. The challenge will be held in conjunction with the 2024 IEEE Spoken Language Technology Workshop (SLT 2024).