Shulin He

speech separation (2) speech enhancement (2) speaker extraction (2) deep learning (1) spectrum modeling (1) speaker embedding (1) speaker recognition (1) real-time processing (1) multi-objective learning (1) generative adversarial network (1) feature fusion (1) audio deepfake detection (1) multi-scale learning (1) complex spectral mapping (1) waveform processing (1) acoustic echo cancellation (1) speech reconstruction (1) speech restoration (1) multi-scale fusion (1) echo path modeling (1)