Speech and singing voice synthesis/convertion/coding

Duration-aware pause insertion using pre-trained language model for multi-speaker text-to-speech

Prosody-controllable spontaneous TTS with neural HMMs

Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing

Analysis and transformation of voice level in singing voice

Context-aware Coherent Speaking Style Prediction with Hierarchical Transformers for Audiobook Speech Synthesis

Ensemble prosody prediction for expressive speech synthesis

Voice-preserving Zero-shot Multiple Accent Conversion

Navigating and Reaching Therapeutic Goals with Dynamical Systems in Conversation-based Interventions

FREEVC: TOWARDS HIGH-QUALITY TEXT-FREE ONE-SHOT VOICE CONVERSION

Enhancement of text-predicting style token with generative adversarial network for expressive speech synthesis

VQ-CL: Learning disentangled speech representations with contrastive learning and vector quantization

EXPRESSIVE-VC: HIGHLY EXPRESSIVE VOICE CONVERSION WITH ATTENTION FUSION OF BOTTLENECK AND PERTURBATION FEATURES