Double Entendre: Robust Audio-Based AI-Generated Lyrics Detection via Multi-View Fusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Frohmann, Markus, Meseguer-Brocal, Gabriel, Schedl, Markus, Epure, Elena V.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908426570825728
author Frohmann, Markus
Meseguer-Brocal, Gabriel
Schedl, Markus
Epure, Elena V.
author_facet Frohmann, Markus
Meseguer-Brocal, Gabriel
Schedl, Markus
Epure, Elena V.
contents The rapid advancement of AI-based music generation tools is revolutionizing the music industry but also posing challenges to artists, copyright holders, and providers alike. This necessitates reliable methods for detecting such AI-generated content. However, existing detectors, relying on either audio or lyrics, face key practical limitations: audio-based detectors fail to generalize to new or unseen generators and are vulnerable to audio perturbations; lyrics-based methods require cleanly formatted and accurate lyrics, unavailable in practice. To overcome these limitations, we propose a novel, practically grounded approach: a multimodal, modular late-fusion pipeline that combines automatically transcribed sung lyrics and speech features capturing lyrics-related information within the audio. By relying on lyrical aspects directly from audio, our method enhances robustness, mitigates susceptibility to low-level artifacts, and enables practical applicability. Experiments show that our method, DE-detect, outperforms existing lyrics-based detectors while also being more robust to audio perturbations. Thus, it offers an effective, robust solution for detecting AI-generated music in real-world scenarios. Our code is available at https://github.com/deezer/robust-AI-lyrics-detection.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15981
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Double Entendre: Robust Audio-Based AI-Generated Lyrics Detection via Multi-View Fusion
Frohmann, Markus
Meseguer-Brocal, Gabriel
Schedl, Markus
Epure, Elena V.
Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
The rapid advancement of AI-based music generation tools is revolutionizing the music industry but also posing challenges to artists, copyright holders, and providers alike. This necessitates reliable methods for detecting such AI-generated content. However, existing detectors, relying on either audio or lyrics, face key practical limitations: audio-based detectors fail to generalize to new or unseen generators and are vulnerable to audio perturbations; lyrics-based methods require cleanly formatted and accurate lyrics, unavailable in practice. To overcome these limitations, we propose a novel, practically grounded approach: a multimodal, modular late-fusion pipeline that combines automatically transcribed sung lyrics and speech features capturing lyrics-related information within the audio. By relying on lyrical aspects directly from audio, our method enhances robustness, mitigates susceptibility to low-level artifacts, and enables practical applicability. Experiments show that our method, DE-detect, outperforms existing lyrics-based detectors while also being more robust to audio perturbations. Thus, it offers an effective, robust solution for detecting AI-generated music in real-world scenarios. Our code is available at https://github.com/deezer/robust-AI-lyrics-detection.
title Double Entendre: Robust Audio-Based AI-Generated Lyrics Detection via Multi-View Fusion
topic Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2506.15981