SongBsAb: A Dual Prevention Approach against Singing Voice Conversion based Illegal Song Covers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Guangke, Zhang, Yedi, Song, Fu, Wang, Ting, Du, Xiaoning, Liu, Yang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909409551056896
author Chen, Guangke
Zhang, Yedi
Song, Fu
Wang, Ting
Du, Xiaoning
Liu, Yang
author_facet Chen, Guangke
Zhang, Yedi
Song, Fu
Wang, Ting
Du, Xiaoning
Liu, Yang
contents Singing voice conversion (SVC) automates song covers by converting a source singing voice from a source singer into a new singing voice with the same lyrics and melody as the source, but sounds like being covered by the target singer of some given target singing voices. However, it raises serious concerns about copyright and civil right infringements. We propose SongBsAb, the first proactive approach to tackle SVC-based illegal song covers. SongBsAb adds perturbations to singing voices before releasing them, so that when they are used, the process of SVC will be interfered, leading to unexpected singing voices. Perturbations are carefully crafted to (1) provide a dual prevention, i.e., preventing the singing voice from being used as the source and target singing voice in SVC, by proposing a gender-transformation loss and a high/low hierarchy multi-target loss, respectively; and (2) be harmless, i.e., no side-effect on the enjoyment of protected songs, by refining a psychoacoustic model-based loss with the backing track as an additional masker, a unique accompanying element for singing voices compared to ordinary speech voices. We also adopt a frame-level interaction reduction-based loss and encoder ensemble to enhance the transferability of SongBsAb to unknown SVC models. We demonstrate the prevention effectiveness, harmlessness, and robustness of SongBsAb on five diverse and promising SVC models, using both English and Chinese datasets, and both objective and human study-based subjective metrics. Our work fosters an emerging research direction for mitigating illegal automated song covers.
format Preprint
id arxiv_https___arxiv_org_abs_2401_17133
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SongBsAb: A Dual Prevention Approach against Singing Voice Conversion based Illegal Song Covers
Chen, Guangke
Zhang, Yedi
Song, Fu
Wang, Ting
Du, Xiaoning
Liu, Yang
Sound
Artificial Intelligence
Cryptography and Security
Machine Learning
Multimedia
Audio and Speech Processing
Singing voice conversion (SVC) automates song covers by converting a source singing voice from a source singer into a new singing voice with the same lyrics and melody as the source, but sounds like being covered by the target singer of some given target singing voices. However, it raises serious concerns about copyright and civil right infringements. We propose SongBsAb, the first proactive approach to tackle SVC-based illegal song covers. SongBsAb adds perturbations to singing voices before releasing them, so that when they are used, the process of SVC will be interfered, leading to unexpected singing voices. Perturbations are carefully crafted to (1) provide a dual prevention, i.e., preventing the singing voice from being used as the source and target singing voice in SVC, by proposing a gender-transformation loss and a high/low hierarchy multi-target loss, respectively; and (2) be harmless, i.e., no side-effect on the enjoyment of protected songs, by refining a psychoacoustic model-based loss with the backing track as an additional masker, a unique accompanying element for singing voices compared to ordinary speech voices. We also adopt a frame-level interaction reduction-based loss and encoder ensemble to enhance the transferability of SongBsAb to unknown SVC models. We demonstrate the prevention effectiveness, harmlessness, and robustness of SongBsAb on five diverse and promising SVC models, using both English and Chinese datasets, and both objective and human study-based subjective metrics. Our work fosters an emerging research direction for mitigating illegal automated song covers.
title SongBsAb: A Dual Prevention Approach against Singing Voice Conversion based Illegal Song Covers
topic Sound
Artificial Intelligence
Cryptography and Security
Machine Learning
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2401.17133