← authors · overview

• Achieving Human Parity in Conversational Speech Recognition
  2016 · 479 citations
• DurIAN: Duration Informed Attention Network For Multimodal Synthesis
  2019 · 94 citations
• End-to-End Multi-Channel Speech Separation
  2019 · 81 citations
• FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis
  2022 · 28 citations
• BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis
  2022 · 26 citations
• Towards Robust Speaker Verification with Target Speaker Enhancement
  2021 · 19 citations
• DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs
  2022 · 19 citations
• Replay and Synthetic Speech Detection with Res2net Architecture
  2020 · 18 citations
• Minimum Bayes Risk Training of RNN-Transducer for End-to-End Speech Recognition
  2019 · 16 citations
• Deep Extractor Network for Target Speaker Recovery From Single Channel Speech Mixtures
  2018 · 14 citations
• Maximizing Mutual Information for Tacotron
  2019 · 13 citations
• DurIAN-SC: Duration Informed Attention Network based Singing Voice Conversion System
  2020 · 13 citations
• Recognizing Multi-talker Speech with Permutation Invariant Training
  2017 · 12 citations
• Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks
  2019 · 11 citations
• Learning Singing From Speech
  2019 · 10 citations