Jian Zhu

phone recognition (3) representation learning (3) multimodal learning (2) multimodal domain adaptation (2) multilingual model (2) low-resource language (2) multilingual speech (2) transformer architecture (2) domain adaptation (2) contrastive learning (2) grapheme-to-phoneme conversion (2) speech synthesis (2) large language model (2) video generation (1) embedding learning (1) benchmark evaluation (1) human perception (1) information bottleneck (1) zero-shot learning (1) text classification (1)