Speech and singing voice synthesis/convertion/coding

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

UNSUPERVISED PRE-TRAINING FOR DATA-EFFICIENT TEXT-TO-SPEECH ON LOW RESOURCE LANGUAGES

LightGrad: Lightweight Diffusion Probabilistic Model for Text-to-Speech

WeSinger 2: Fully Parallel Singing Voice Synthesis via Multi-Singer Conditional Adversarial Training

NSV-TTS: NON-SPEECH VOCALIZATION MODELING AND TRANSFER IN EMOTIONAL TEXT-TO-SPEECH

WAVE-U-NET DISCRIMINATOR: FAST AND LIGHTWEIGHT DISCRIMINATOR FOR GENERATIVE ADVERSARIAL NETWORK-BASED SPEECH SYNTHESIS

SYNTACC : Synthesizing multi-accent speech by weight factorization

Modelling low-resource accents without accent-specific TTS frontend

Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocoder

VF-TACO2: TOWARDS FAST AND LIGHTWEIGHT SYNTHESIS FOR AUTOREGRESSIVE MODELS WITH VARIATION AUTOENCODER AND FEATURE DISTILLATION

Low-latency electrolaryngeal speech enhancement based on FastSpeech2-based voice conversion and self-supervised speech representation

TEXT-TO-SPEECH SYNTHESIS FROM DARK DATA WITH EVALUATION-IN-THE-LOOP DATA SELECTION