Speech and singing voice synthesis/convertion/coding

Streaming Voice Conversion Via Intermediate Bottleneck Features And Non-streaming Teacher Guidance

Text-to-speech synthesis based on latent variable conversion using diffusion probabilistic model and variational autoencoder

Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-to-Speech

ZERO-SHOT PERSONALIZED LIP-TO-SPEECH SYNTHESIS WITH FACE IMAGE BASED VOICE CONTROL

PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping