Kang Y, Liu T, Li H, Hao Y, Ding W. Self-Supervised Audio-and-Text Pre-training with Extremely Low-Resource Parallel Data. AAAI [Internet]. 2022Jun.28 [cited 2024Nov.23];36(10):10875-83. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/21334