@misc{https://doi.org/10.48550/arxiv.2006.11477,
 doi = {10.48550/ARXIV.2006.11477},
 
 url = {https://arxiv.org/abs/2006.11477},
 
 author = {Baevski, Alexei and Zhou, Henry and Mohamed, Abdelrahman and Auli, Michael},
 
 keywords = {Computation and Language (cs.CL), Machine Learning (cs.LG), Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering},
 
 title = {wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations},
 
 publisher = {arXiv},


@misc{https://doi.org/10.48550/arxiv.2105.01051,
 doi = {10.48550/ARXIV.2105.01051},
 
 url = {https://arxiv.org/abs/2105.01051},
 
 author = {Yang, Shu-wen and Chi, Po-Han and Chuang, Yung-Sung and Lai, Cheng-I Jeff and Lakhotia, Kushal and Lin, Yist Y. and Liu, Andy T. and Shi, Jiatong and Chang, Xuankai and Lin, Guan-Ting and Huang, Tzu-Hsien and Tseng, Wei-Cheng and Lee, Ko-tik and Liu, Da-Rong and Huang, Zili and Dong, Shuyan and Li, Shang-Wen and Watanabe, Shinji and Mohamed, Abdelrahman and Lee, Hung-yi},
 
 keywords = {Computation and Language (cs.CL), Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering},
 
 title = {SUPERB: Speech processing Universal PERformance Benchmark},
 
 publisher = {arXiv},
 
 year = {2021},
}