Authors: Canjie Luo, Qingxiang Lin, Tianwei Wang, Lu Yang, Linjiang Zhang, Canyu Xie, Jiapeng Wang, Peng Wang, Hui Li, Yaoxiong Huang, Zecheng Xie, Yuliang Liu,Lianwen Jin,Chunhua Shen,Yaqiang Wu,Liangwei Wang

Description: This method utilizes an ensembled model, which consists of attention-based network, transformer network and CTC-based network. Apart from the official training dataset, about 2 million synthesized samples are used for training. The result is submitted by the researchers from South China University of Technology, Northwestern Polytechnical University, The University of Adelaide, Lenovo and Huawei. The researchers are Canjie Luo, Qingxiang Lin, Tianwei Wang, Lu Yang, Linjiang Zhang, Canyu Xie, Jiapeng Wang, Peng Wang, Hui Li, Yaoxiong Huang, Zecheng Xie, Yuliang Liu, Lianwen Jin, Chunhua Shen, Yaqiang Wu and Liangwei Wang.

单位：华南理工大学，阿德莱德大学，西北工业大学，联想，华为。
作者：罗灿杰，林庆祥，王天玮，杨路，张林江，谢灿宇，汪嘉鹏，王鹏，李晖，黄耀雄，谢泽澄，刘禹良，金连文，沈春华，武亚强，王靓伟。