Meng Ge

speaker extraction (5) speech enhancement (5) neural network (4) attention mechanism (3) representation learning (3) graph neural network (3) convolutional neural network (2) audio-visual speaker extraction (2) speech separation (2) self-supervised learning (2) automatic speech recognition (2) sound source localization (2) node classification (2) graph representation (2) direction of arrival (2) multi-talker speech (2) multimodal learning (1) speech recognition (1) unsupervised pretraining (1) knowledge distillation (1)