← authors · overview

• VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis
  2021 · 10 citations
• Deep Feed-forward Sequential Memory Networks for Speech Synthesis
  2018 · 8 citations
• Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis
  2022 · 1 citations
• Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features
  2022 · 1 citations
• DeepASMR: LLM-Based Zero-Shot ASMR Speech Generation for Anyone of Any Voice
  2026
• UrgentMOS: Unified Multi-Metric and Preference Learning for Robust Speech Quality Assessment
  2026
• REF-VC: Robust, Expressive and Fast Zero-Shot Voice Conversion with Diffusion Transformers
  2025
• MacST: Multi-Accent Speech Synthesis via Text Transliteration for Accent Conversion
  2024
• One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation
  2021