Zhiyong Yan

audio encoder (2) audio tagging (2) speech corpus (2) transfer learning (2) non-native speech (1) multimodal learning (1) self-supervised learning (1) automatic speech recognition (1) speech recognition (1) cross-modal retrieval (1) keyword spotting (1) speaker embedding (1) audio-text retrieval (1) semi-supervised training (1) convolutional neural network (1) model architecture (1) noise robustness (1) language model (1) low-rank adaptation (1) audio classification (1)