 Building Blocks for a Complex-Valued Transformer ArchitectureIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 |
 D2Former: A Fully Complex Dual-Path Dual-Decoder Conformer Network using
Joint Complex Masking and Complex Spectral Mapping for Monaural Speech
EnhancementIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 |
 Uformer: A Unet based dilated complex & real dual-path conformer network
for simultaneous speech enhancement and dereverberationIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021 |
 Signal Transformer: Complex-valued Attention and Meta-Learning for
Signal RecognitionIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021 |
 Residual Shuffle-Exchange Networks for Fast Processing of Long SequencesAAAI Conference on Artificial Intelligence (AAAI), 2020 |
