Ying Shi

speech recognition (2) keyword spotting (2) self-supervised learning (1) data augmentation (1) speaker verification (1) convolutional neural network (1) deep neural network (1) multi-talker speech recognition (1) serialized output training (1) noisy speech (1) attention encoder-decoder (1) permutation invariant training (1) dominance scoring (1) text-independent verification (1) speaker feature learning (1) time-delay deep neural network (1) speaker trait extraction (1) mix training (1) mixed speech (1) few-shot learning (1)