← authors · overview

• New Insights on Target Speaker Extraction
  2022 · 15 citations
• AmbiSep: Ambisonic-to-Ambisonic Reverberant Speech Separation Using Transformer Networks
  2022 · 9 citations
• Beamformer-Guided Target Speaker Extraction
  2023 · 9 citations
• A Hybrid Approach for Low-Complexity Joint Acoustic Echo and Noise Reduction
  2024 · 3 citations
• Contrastive Representation Learning for Acoustic Parameter Estimation
  2023 · 1 citations
• Quantifying the Uncertainty of Blindly Estimated Room Embeddings Using a Dispersion-Calibrated Score
  2026
• A Comparison of Generative and Discriminative Methods for Speech Enhancement: Robustness, Complexity, and Hallucination
  2026
• Robust Speech Activity Detection in the Presence of Singing Voice
  2025
• Acoustic Teleportation via Disentangled Neural Audio Codec Representations
  2025
• GAN-Based Multi-Microphone Spatial Target Speaker Extraction
  2025
• Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancement
  2025
• Dynamic Slimmable Networks for Efficient Speech Separation
  2025
• Benchmarking Neural Speech Codec Intelligibility with SITool
  2025
• Speaker Verification in Multi-Speaker Environments Using Temporal Feature Fusion
  2022
• Meta Learning Text-to-Speech Synthesis in over 7000 Languages
  2024