Ziyang Ma

large language model (5) automatic speech recognition (5) self-supervised learning (4) speech synthesis (4) multimodal learning (3) zero-shot learning (2) speech representation (2) image reconstruction (2) end-to-end model (2) speech emotion recognition (2) representation learning (2) low-resource language (2) music understanding (2) video generation (1) uncertainty quantification (1) benchmark evaluation (1) curriculum learning (1) em algorithm (1) active learning (1) k-means clustering (1)