[HTML][HTML] Adversarial attack and defense strategies of speaker recognition systems: A survey

H Tan, L Wang, H Zhang, J Zhang, M Shafiq, Z Gu - Electronics, 2022‏ - mdpi.com
Speaker recognition is a task that identifies the speaker from multiple audios. Recently,
advances in deep learning have considerably boosted the development of speech signal …

[PDF][PDF] Convolutional Recurrent Neural Network and Multitask Learning for Manipulation Region Location.

K Li, XM Zeng, JT Zhang, Y Song - DADA@ IJCAI, 2023‏ - addchallenge.cn
In this paper, we present our proposed system on Audio Deepfake Detection Challenge
(ADD) 2023 Track 2-Manipulation region location (RL). Speech synthesis and voice …

Voting for the right answer: Adversarial defense for speaker verification

H Wu, Y Zhang, Z Wu, D Wang, H Lee - arxiv preprint arxiv:2106.07868, 2021‏ - arxiv.org
Automatic speaker verification (ASV) is a well developed technology for biometric
identification, and has been ubiquitous implemented in security-critic applications, such as …