Jie Jia

speech enhancement (4) attention mechanism (1) knowledge distillation (1) channel attention (1) deep learning (1) convolutional neural network (1) deep neural network (1) feature fusion (1) multi-head attention (1) encoder-decoder architecture (1) feature transfer (1) supervised attention (1) monaural speech enhancement (1) audio-visual speech enhancement (1) temporal context (1) audio-visual feature (1) global-local dependency (1) dilated encoder-decoder (1) multi-stage architecture (1) teacher student (1)