Ge Zhu

speaker verification (2) multi-task learning (1) text classification (1) data augmentation (1) speech processing (1) automatic speech recognition (1) speaker embedding (1) speaker recognition (1) waveform encoder (1) speech classification (1) audio classification (1) benchmark dataset (1) synthetic speech detection (1) multi-scale feature (1) voice activity detection (1) time delay neural network (1) raw waveform (1) squeeze-and-excitation block (1) multi-scale encoder (1) countermeasure system (1)