Weiyi Zheng

automatic speech recognition (3) word error rate (2) semi-supervised learning (1) few-shot learning (1) transfer learning (1) domain adaptation (1) self-supervised learning (1) natural language understanding (1) model scaling (1) text-to-speech synthesis (1) style embedding (1) rnn transducer (1) semantic distance (1) style extraction (1) user perception (1) federated learning (1) speech recognition quality (1) zero-shot learning (1)