Yongjie Lv, Longbiao Wang, Meng Ge, Sheng Li 0010, Chenchen Ding, Lixin Pan, Yuguang Wang, Jianwu Dang, Kiyoshi Honda. Compressing Transformer-Based ASR Model by Task-Driven Loss and Attention-Based Multi-Level Feature Distillation. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022. pages 7992-7996, IEEE, 2022. [doi]
Abstract is missing.