Kaizhi Qian

Synthesis (1)

automatic speech recognition (4) voice conversion (3) unsupervised learning (3) representation learning (3) zero-shot learning (3) self-supervised learning (3) speech recognition (2) speech processing (2) model pruning (2) speech representation (2) transfer learning (2) speech synthesis (2) speech enhancement (2) multimodal generation (2) knowledge transfer (1) autoregressive transformer (1) style transfer (1) information bottleneck (1) few-shot learning (1) bayesian inference (1)