Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Liping, Lee, Kong Aik, Ling, Zhen-Hua, Wang, Xin, Das, Rohan Kumar, Toda, Tomoki, Li, Haizhou
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2509.06361
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912577674543104
author Chen, Liping
Lee, Kong Aik
Ling, Zhen-Hua
Wang, Xin
Das, Rohan Kumar
Toda, Tomoki
Li, Haizhou
author_facet Chen, Liping
Lee, Kong Aik
Ling, Zhen-Hua
Wang, Xin
Das, Rohan Kumar
Toda, Tomoki
Li, Haizhou
contents In the era of big data, remarkable advancements have been achieved in personalized speech generation techniques that utilize speaker attributes, including voice and speaking style, to generate deepfake speech. This has also amplified global security risks from deepfake speech misuse, resulting in considerable societal costs worldwide. To address the security threats posed by deepfake speech, techniques have been developed focusing on both the protection of voice attributes and the defense against deepfake speech. Among them, the voice anonymization technique has been developed to protect voice attributes from extraction for deepfake generation, while deepfake detection and watermarking have been utilized to defend against the misuse of deepfake speech. This paper provides a short and concise overview of the three techniques, describing the methodologies, advancements, and challenges. A comprehensive version, offering additional discussions, will be published in the near future.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06361
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Speaker Privacy and Security in the Big Data Era: Protection and Defense against Deepfake
Chen, Liping
Lee, Kong Aik
Ling, Zhen-Hua
Wang, Xin
Das, Rohan Kumar
Toda, Tomoki
Li, Haizhou
Audio and Speech Processing
In the era of big data, remarkable advancements have been achieved in personalized speech generation techniques that utilize speaker attributes, including voice and speaking style, to generate deepfake speech. This has also amplified global security risks from deepfake speech misuse, resulting in considerable societal costs worldwide. To address the security threats posed by deepfake speech, techniques have been developed focusing on both the protection of voice attributes and the defense against deepfake speech. Among them, the voice anonymization technique has been developed to protect voice attributes from extraction for deepfake generation, while deepfake detection and watermarking have been utilized to defend against the misuse of deepfake speech. This paper provides a short and concise overview of the three techniques, describing the methodologies, advancements, and challenges. A comprehensive version, offering additional discussions, will be published in the near future.
title Speaker Privacy and Security in the Big Data Era: Protection and Defense against Deepfake
topic Audio and Speech Processing
url https://arxiv.org/abs/2509.06361