Cunhang Fan

Cunhang Fan

School of Computer Science and Technology,Anhui University

Cunhang Fan（范存航）

I received the Ph.D degree with the National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China, in 2021, and the B.S. degree from the Beijing University of Chemical Technology (BUCT), Beijing, China, in 2016. I am currently an associate professor with the School of Computer Science and Technology, Anhui University, Heifei, China. My current research interests include brain-computer interface and speech processing.

My research interests include:

  • Speech Processing (Speech Enhancement and Separation, ASR, Fake Speech Detection)

  • Brain-Computer Interface (Auditory Attention Decoding)

News:

  • The paper “Cross-Modal Knowledge Distillation with Multi-Stage Adaptive Feature Fusion for Speech Separation” has been accepted by IEEE/ACM Transactions on Audio, Speech, and Language Processing（CAAI A）
  • The paper “Seeing Helps Hearing: A Multi-modal Dataset and a Mamba-based Dual Branch Parallel Network for Auditory Attention Decoding “ has been accepted by Information Fusion (中科院一区top，CAAI A，CCF B)
  • The paper “Improved Feature Extraction Network for Neuro-Oriented Target Speaker Extraction” has been accepted by ICASSP 2025 (CCF B)
  • The paper “SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG” has been accepted by ICASSP 2025 (CCF B)
  • The paper “BSDB-Net:Band-Split Dual-Branch Network with Selective State Spaces Mechanism for Monaural Speech Enhancement” has been accepted by AAAI 2025 (CCF A)
  • The paper “Region-Based Optimization in Continual Learning for Audio Deepfake Detection” has been accepted by AAAI 2025 (CCF A)
  • The paper “DARNet: Dual Attention Refinement Network with Spatiotemporal Construction for Auditory Attention Detection” has been accepted by NeurIPS 2024 (CCF A)
  • The paper “Multimodal Cross-lingual Summarization for Videos: A Revisit in Knowledge Distillation Induced Triple-stage Training Method” has been accepted by IEEE TPAMI (IF: 20.8，中科院一区top，CCF A)