3 papers
eess.AS2024
CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder
Jianwei Cui, Yu Gu, Shihao Chen +3
Singing Voice Synthesis (SVS) aims to generate singing voices of high fidelity and expressiveness. Conventional SVS systems usually utilize an acoustic model to transform a music s…
cs.SD2024
On the Generation and Removal of Speaker Adversarial Perturbation for Voice-Privacy Protection
Chenyang Guo, Liping Chen, Zhuhai Li +3
Neural networks are commonly known to be vulnerable to adversarial attacks mounted through subtle perturbation on the input data. Recent development in voice-privacy protection has…
eess.AS2024
Refining Self-Supervised Learnt Speech Representation using Brain Activations
Hengyu Li, Kangdi Mei, Zhaoci Liu +4
It was shown in literature that speech representations extracted by self-supervised pre-trained models exhibit similarities with brain activations of human for speech perception an…