Compressing Transformer-Based ASR Model by Task-Driven Loss and Attention-Based Multi-Level Feature Distillation - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

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]

This author has not been identified. Look up 'Yongjie Lv' in GoogleThis author has not been identified. Look up 'Longbiao Wang' in GoogleThis author has not been identified. Look up 'Meng Ge' in GoogleThis author has not been identified. Look up 'Sheng Li 0010' in GoogleThis author has not been identified. Look up 'Chenchen Ding' in GoogleThis author has not been identified. Look up 'Lixin Pan' in GoogleThis author has not been identified. Look up 'Yuguang Wang' in GoogleThis author has not been identified. Look up 'Jianwu Dang' in GoogleThis author has not been identified. Look up 'Kiyoshi Honda' in Google

runs on WebDSL