Ziyang Ma

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