Transformer Model Compression for End-to-End Speech Recognition on Mobile Devices-Reference-Cited by-同舟云学术

Transformer Model Compression for End-to-End Speech Recognition on Mobile Devices

Published:2022-08-29 Issue: Volume: Page:
ISSN:
Container-title:2022 30th European Signal Processing Conference (EUSIPCO)
language:
Short-container-title:

Author:

Letaifa Leila Ben¹,Rouas Jean-Luc¹

Affiliation:

1. Univ. de Bordeaux,LaBRI, CNRS UMR 5800, Bordeaux INP,Talence,France

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9908519/9909515/09909765.pdf?arnumber=9909765

Reference25 articles.

1. Quantized neural networks: Training neural networks with low pre-cision weights and activations;hubara;The Journal of Machine Learning Research,2017

2. Optimal brain damage;lecun;Advances in neural information processing systems,1989

3. Knowledge Distillation Using Output Errors for Self-attention End-to-end Models

4. Compressing pre-trained language models by matrix decomposition;noach;International Joint Conference on Natural Language Processing,2020

5. Compressing Large-Scale Transformer-Based Models: A Case Study on BERT

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Electrothermal modeling of junctionless vertical Si nanowire transistors for 3D logic circuit design;ESSDERC 2023 - IEEE 53rd European Solid-State Device Research Conference (ESSDERC);2023-09-11

2. Data-Free Backbone Fine-Tuning for Pruned Neural Networks;2023 31st European Signal Processing Conference (EUSIPCO);2023-09-04

3. Fine-grained analysis of the transformer model for efficient pruning;2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA);2022-12