Kang, Y., T. Liu, H. Li, Y. Hao, and W. Ding. “Self-Supervised Audio-and-Text Pre-Training With Extremely Low-Resource Parallel Data”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 10, June 2022, pp. 10875-83, doi:10.1609/aaai.v36i10.21334.