Login / Signup
Compressing Transformer-Based ASR Model by Task-Driven Loss and Attention-Based Multi-Level Feature Distillation.
Yongjie Lv
Longbiao Wang
Meng Ge
Sheng Li
Chenchen Ding
Lixin Pan
Yuguang Wang
Jianwu Dang
Kiyoshi Honda
Published in:
ICASSP (2022)
Keyphrases
</>
computational model
mathematical model
probabilistic model
theoretical framework
parameter estimation
experimental data
formal model
multi layer
high level
face recognition
feature extraction
data driven
theoretical analysis