Study of Positional Encoding Approaches for Audio Spectrogram Transformers

Author:

Pepino Leonardo1,Riera Pablo1,Ferrer Luciana1

Affiliation:

1. CONICET-UBA,Instituto de Investigación en Ciencias de la Computación (ICC),Argentina

Funder

Google

Publisher

IEEE

Reference30 articles.

1. Learning Environmental Sounds with Multi-scale Convolutional Neural Network

2. AST: Audio Spectrogram Transformer

3. Audio transformers: Transformer architectures for large scale audio understanding. adieu convolutions;verma,2021

4. Conditional positional encodings for vision transformers;chu,2021

5. Roformer: Enhanced transformer with rotary position embedding;su,2021

Cited by 4 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. Inductive Bias Integration for Transformer Enhancement in Small-scale Segmentation Tasks;Proceedings of the 2024 5th International Conference on Computing, Networks and Internet of Things;2024-05-24

2. Task-driven common subspace learning based semantic feature extraction for acoustic event recognition;Expert Systems with Applications;2023-12

3. Multimodal knowledge graph construction of Chinese traditional operas and sentiment and genre recognition;Journal of Cultural Heritage;2023-07

4. Machine Learning-based Energy Consumption Model for Data Center;2023 35th Chinese Control and Decision Conference (CCDC);2023-05-20

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