Showing 2024Show all
3 papers · 1 filter
cs.SD2024
EmoAttack: Utilizing Emotional Voice Conversion for Speech Backdoor Attacks on Deep Speech Classification Models
Wenhan Yao, Zedong XingXiarun Chen, Jia Liu +2
Deep speech classification tasks, mainly including keyword spotting and speaker verification, play a crucial role in speech-based human-computer interaction. Recently, the security…
cs.SD2024
Pureformer-VC: Non-parallel One-Shot Voice Conversion with Pure Transformer Blocks and Triplet Discriminative Training
Wenhan Yao, Zedong Xing, Xiarun Chen +3
One-shot voice conversion(VC) aims to change the timbre of any source speech to match that of the target speaker with only one speech sample. Existing style transfer-based VC metho…
cs.SD2024
Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition
Wenhan Yao, Jiangkun Yang, Yongqiang He +2
Speech recognition is an essential start ring of human-computer interaction, and recently, deep learning models have achieved excellent success in this task. However, when the mode…