← authors · overview

• Semi-supervised Time Domain Target Speaker Extraction with Attention
  2022 · 7 citations
• PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss
  2020 · 6 citations
• Real-time Stereo Speech Enhancement with Spatial-Cue Preservation based on Dual-Path Structure
  2024 · 5 citations
• A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement
  2023 · 2 citations
• A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech
  2020 · 1 citations
• Semi-Supervised Singing Voice Separation with Noisy Self-Training
  2021 · 1 citations
• Masked Autoencoders as Universal Speech Enhancer
  2026
• Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders
  2021
• Personalized PercepNet: Real-time, Low-complexity Target Voice Separation and Enhancement
  2021
• Improved singing voice separation with chromagram-based pitch-aware remixing
  2022