Adapting General Disentanglement-Based Speaker Anonymization for Enhanced Emotion Preservation

X Miao, Y Zhang, X Wang, N Tomashenko… - arXiv preprint arXiv …, 2024 - arxiv.org
A general disentanglement-based speaker anonymization system typically separates
speech into content, speaker, and prosody features using individual encoders. This paper …

Controlling your Attributes in Voice

X Li, ZS Wang, P Zhang - arXiv preprint arXiv:2501.01674, 2025 - arxiv.org
Attribute control in generative tasks aims to modify personal attributes, such as age and
gender while preserving the identity information in the source sample. Although significant …