Skip to content
conftrace_

voice style transfer

5 papers

Explore in graph

Also known as

VST

Co-occurring keywords · papers mentioning both

speaker embedding (2) voice conversion (2) self-supervised learning (2) zero-shot learning (2) end-to-end synthesis (1) speech conversion (1) location-variable convolution (1) information-theoretic guidance (1) disentangled representation learning (1) lombard speech (1)

Papers

End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions Interspeech 2023 HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer Interspeech 2023 Improving Zero-Shot Voice Style Transfer via Disentangled Representation Learning ICLR 2021 VoiceMixer: Adversarial Voice Style Mixup NeurIPS 2021 Augmented CycleGANs for Continuous Scale Normal-to-Lombard Speaking Style Conversion Interspeech 2019