Adapting General Disentanglement-Based Speaker Anonymization for Enhanced Emotion Preservation
A general disentanglement-based speaker anonymization system typically separates
speech into content, speaker, and prosody features using individual encoders. This paper …
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 …
gender while preserving the identity information in the source sample. Although significant …