FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization

Zhengkun Tian, Jiangyan Yi, Ye Bai, Jianhua Tao, Shuai Zhang 0014, Zhengqi Wen. FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization. In Hynek Hermansky, Honza Cernocký, Lukás Burget, Lori Lamel, Odette Scharenborg, Petr Motlícek, editors, Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021. pages 4034-4038, ISCA, 2021. [doi]

@inproceedings{TianYBT0W21,
  title = {FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization},
  author = {Zhengkun Tian and Jiangyan Yi and Ye Bai and Jianhua Tao and Shuai Zhang 0014 and Zhengqi Wen},
  year = {2021},
  doi = {10.21437/Interspeech.2021-1367},
  url = {https://doi.org/10.21437/Interspeech.2021-1367},
  researchr = {https://researchr.org/publication/TianYBT0W21},
  cites = {0},
  citedby = {0},
  pages = {4034-4038},
  booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021},
  editor = {Hynek Hermansky and Honza Cernocký and Lukás Burget and Lori Lamel and Odette Scharenborg and Petr Motlícek},
  publisher = {ISCA},
}