Aaron (Yinghao) Li

StyleTTS2. StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

StarGANv2-VC. StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

StyleTTS. Official Implementation of StyleTTS

DMOSpeech2. Python

PL-BERT. Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions

HiFTNet. HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform

StyleTTS-VC. Official Implementation of StyleTTS-VC

StyleTTS-ZS. StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion

PitchExtractor. Deep Neural Pitch Extractor for Voice Conversion and TTS Training

AuxiliaryASR. Joint CTC-S2S Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)

SLMGAN. SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANs