← authors · overview

• Convolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separation
  2021 · 32 citations
• TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
  2024 · 20 citations
• Leveraging Low-Distortion Target Estimates for Improved Speech Enhancement
  2021 · 12 citations
• Convolutive Prediction for Reverberant Speech Separation
  2021 · 10 citations
• TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings
  2023 · 2 citations
• Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction
  2023 · 1 citations
• Technical Report for MERL's Real-TSE Challenge Submission
  2026
• Predictive-Generative Drift Decomposition for Speech Enhancement and Separation
  2026
• HASRD: Hierarchical Acoustic and Semantic Representation Disentanglement
  2025
• Factorized RVQ-GAN For Disentangled Speech Tokenization
  2025
• STFT-Domain Neural Speech Enhancement with Very Low Algorithmic Latency
  2022
• Cold Diffusion for Speech Enhancement
  2022
• Enhanced Reverberation as Supervision for Unsupervised Speech Separation
  2024