 UniArray: Unified Spectral-Spatial Modeling for Array-Geometry-Agnostic Speech SeparationIEEE Signal Processing Letters (IEEE SPL), 2025 |
 GPU-accelerated Guided Source Separation for Meeting TranscriptionInterspeech (Interspeech), 2022 |
 Bayesian Neural Network Language Modeling for Speech RecognitionIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2022 |
 Audio-visual multi-channel speech separation, dereverberation and
recognitionIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 |
 Recent Progress in the CUHK Dysarthric Speech Recognition SystemIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2022 |
 TS-RIR: Translated synthetic room impulse responses for speech
augmentationAutomatic Speech Recognition & Understanding (ASRU), 2021 |
 Multi-channel Multi-frame ADL-MVDR for Target Speech SeparationIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2020 |
