Adversarial speech for voice privacy protection from Personalized Speech generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Shihao, Chen, Liping, Zhang, Jie, Lee, KongAik, Ling, Zhenhua, Dai, Lirong
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917689022218240
author Chen, Shihao
Chen, Liping
Zhang, Jie
Lee, KongAik
Ling, Zhenhua
Dai, Lirong
author_facet Chen, Shihao
Chen, Liping
Zhang, Jie
Lee, KongAik
Ling, Zhenhua
Dai, Lirong
contents The rapid progress in personalized speech generation technology, including personalized text-to-speech (TTS) and voice conversion (VC), poses a challenge in distinguishing between generated and real speech for human listeners, resulting in an urgent demand in protecting speakers' voices from malicious misuse. In this regard, we propose a speaker protection method based on adversarial attacks. The proposed method perturbs speech signals by minimally altering the original speech while rendering downstream speech generation models unable to accurately generate the voice of the target speaker. For validation, we employ the open-source pre-trained YourTTS model for speech generation and protect the target speaker's speech in the white-box scenario. Automatic speaker verification (ASV) evaluations were carried out on the generated speech as the assessment of the voice protection capability. Our experimental results show that we successfully perturbed the speaker encoder of the YourTTS model using the gradient-based I-FGSM adversarial perturbation method. Furthermore, the adversarial perturbation is effective in preventing the YourTTS model from generating the speech of the target speaker. Audio samples can be found in https://voiceprivacy.github.io/Adeversarial-Speech-with-YourTTS.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11857
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adversarial speech for voice privacy protection from Personalized Speech generation
Chen, Shihao
Chen, Liping
Zhang, Jie
Lee, KongAik
Ling, Zhenhua
Dai, Lirong
Audio and Speech Processing
Sound
The rapid progress in personalized speech generation technology, including personalized text-to-speech (TTS) and voice conversion (VC), poses a challenge in distinguishing between generated and real speech for human listeners, resulting in an urgent demand in protecting speakers' voices from malicious misuse. In this regard, we propose a speaker protection method based on adversarial attacks. The proposed method perturbs speech signals by minimally altering the original speech while rendering downstream speech generation models unable to accurately generate the voice of the target speaker. For validation, we employ the open-source pre-trained YourTTS model for speech generation and protect the target speaker's speech in the white-box scenario. Automatic speaker verification (ASV) evaluations were carried out on the generated speech as the assessment of the voice protection capability. Our experimental results show that we successfully perturbed the speaker encoder of the YourTTS model using the gradient-based I-FGSM adversarial perturbation method. Furthermore, the adversarial perturbation is effective in preventing the YourTTS model from generating the speech of the target speaker. Audio samples can be found in https://voiceprivacy.github.io/Adeversarial-Speech-with-YourTTS.
title Adversarial speech for voice privacy protection from Personalized Speech generation
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2401.11857