@article{maskedautoencoderswithmultiwindow, title = {Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners}, author = {Sarthak Yadav and Sergios Theodoridis and Lars Kai Hansen and Zheng-Hua Tan}, year = {2023}, eprint = {2306.00561}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2306.00561v2}, }