Efficient Large-Scale Audio Tagging Via Transformer-to-CNN Knowledge Distillation-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Efficient Large-Scale Audio Tagging Via Transformer-to-CNN Knowledge Distillation

Published:2023-06-04 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Schmid Florian¹,Koutini Khaled²,Widmer Gerhard¹

Affiliation:

1. Institute of Computational Perception (CP-JKU)

2. Johannes Kepler University,LIT Artificial Intelligence Lab,Linz,Austria

Funder

European Research Council

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10094559/10094560/10096110.pdf?arnumber=10096110

Reference25 articles.

1. Training data-efficient image transformers & distillation through attention;touvron;ICML,2021

2. An image is worth 16x16 words: Transformers for image recognition at scale;dosovitskiy;ICLRE,2021

3. Masked autoencoders that listen;huang;CoRR,2022

4. A ConvNet for the 2020s

5. Attention is all you need;vaswani;NIPS,2017

Cited by 17 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. A deep learning approach to dysphagia-aspiration detecting algorithm through pre- and post-swallowing voice changes;Frontiers in Bioengineering and Biotechnology;2024-08-02

2. MTGNet: multi-label mesh quality evaluation using topology-guided graph neural network;Engineering with Computers;2024-06-01

3. Model compression of deep neural network architectures for visual pattern recognition: Current status and future directions;Computers and Electrical Engineering;2024-05

4. CED: Consistent Ensemble Distillation for Audio Tagging;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

5. Prediction of dysphagia aspiration through machine learning-based analysis of patients’ postprandial voices;Journal of NeuroEngineering and Rehabilitation;2024-03-30

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号京ICP备18003416号-3