Speech and singing voice synthesis/convertion/coding

DiffVoice: Text-to-Speech with Latent Diffusion

IMPROVED APPLIANCE TRANSIENT FEATURE EXTRACTION VIA TEMPLATE MATCHING

DSPGAN: a GAN-based universal vocoder for high-fidelity TTS by time-frequency domain supervision from DSP

PHONEix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation with Phoneme Distribution Predictor

DELIVERING SPEAKING STYLE IN LOW-RESOURCE VOICE CONVERSION WITH MULTI-FACTOR CONSTRAINTS

ACE-VC: Adaptive and Controllable Voice Conversion using Explicitly Disentangled Self-supervised Speech Representations

Learning interpretable filters in Wav-Unet for speech enhancement

Preserving background sound in noise-robust voice conversion via multi-task learning

PUFFIN: PITCH-SYNCHRONOUS NEURAL WAVEFORM GENERATION FOR FULLBAND SPEECH ON MODEST DEVICES

Singing Voice Synthesis Based on a Musical Note Position-aware Attention Mechanism

Enhancing the Vocal Range of Single-Speaker Singing Voice Synthesis with Melody-Unsupervised Pre-training

Embedding a differentiable mel-cepstral synthesis filter to a neural speech synthesis system