ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Deep mutual attention network for acoustic scene classification

Xie, Wei; He, Qianhua*; Yu, Zitong; Li, Yanxiong
Digital Signal Processing: A Review Journal2022-4-30DOI: 10.1016/j.dsp.2022.103450
7被引11阅读
引用收藏
分享

摘要

Fusion strategies that utilize time-frequency features have achieved superior performance in acoustic scene classification tasks. However, the existing fusion schemes are mainly frameworks that involve different modules for feature learning, fusion, and modeling. These frameworks are prone to introduce artificial interference and thus make it challenging to obtain the system's best performance. In addition, the lack of adequate information interaction between different features in the existing fusion schemes prevents the learned features from achieving the optimal discriminative ability. To tackle these problems, we design a deep mutual attention network based on the principle of receptive field regularization and the mutual attention mechanism. The proposed network can realize the joint learning and complementary enhancement of multiple time-frequency features end-to-end, which improves features' learning efficiency and discriminative ability. Experimental results on six publicly available datasets show that the proposed network outperforms almost all state-of-the-art systems regarding classification accuracy.

学科与关键词

关键词
Acoustic scene classificationAttention mechanismDeep mutual attention networkTime-frequency featureComplementary enhancement
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
Digital Signal Processing: A Review Journal
发表日期
2022-04-30
卷期
第 123 卷
页码
103450
DOI
10.1016/j.dsp.2022.103450
语言
ENGLISH
期刊等级
2区
成果收录
SCIE
资助标注
National Natural Science Foundation of China [61771200, 62111530145]; international scientific research collaboration project of Guangdong Province, China [2021A0505030003]; Guangdong Basic and Applied Basic Research Foundation, China [2021A1515011454]

作者

  • X

    Xie, Wei (第一作者)

  • H

    He, Qianhua (通讯)

查看全部 4 位作者收起作者
  • Y

    Yu, Zitong

  • L

    Li, Yanxiong

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417