Environmental sound classification using temporal-frequency attention based convolutional neural network

Abstract Environmental sound classification is one of the important issues in the audio recognition field. Compared with structured sounds such as speech and music, the time–frequency structure of environmental sounds is more complicated. In order to learn time and frequency features from Log-Mel sp...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wenjie Mu, Bo Yin, Xianqing Huang, Jiali Xu, Zehua Du
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/9ccc492d96474e4386fdec45cd0445a2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9ccc492d96474e4386fdec45cd0445a2
record_format	dspace
spelling	oai:doaj.org-article:9ccc492d96474e4386fdec45cd0445a22021-11-08T10:50:28ZEnvironmental sound classification using temporal-frequency attention based convolutional neural network10.1038/s41598-021-01045-42045-2322https://doaj.org/article/9ccc492d96474e4386fdec45cd0445a22021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-01045-4https://doaj.org/toc/2045-2322Abstract Environmental sound classification is one of the important issues in the audio recognition field. Compared with structured sounds such as speech and music, the time–frequency structure of environmental sounds is more complicated. In order to learn time and frequency features from Log-Mel spectrogram more effectively, a temporal-frequency attention based convolutional neural network model (TFCNN) is proposed in this paper. Firstly, an experiment that is used as motivation in proposed method is designed to verify the effect of a specific frequency band in the spectrogram on model classification. Secondly, two new attention mechanisms, temporal attention mechanism and frequency attention mechanism, are proposed. These mechanisms can focus on key frequency bands and semantic related time frames on the spectrogram to reduce the influence of background noise and irrelevant frequency bands. Then, a feature information complementarity is formed by combining these mechanisms to more accurately capture the critical time–frequency features. In such a way, the representation ability of the network model can be greatly improved. Finally, experiments on two public data sets, UrbanSound 8 K and ESC-50, demonstrate the effectiveness of the proposed method.Wenjie MuBo YinXianqing HuangJiali XuZehua DuNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Wenjie Mu Bo Yin Xianqing Huang Jiali Xu Zehua Du Environmental sound classification using temporal-frequency attention based convolutional neural network
description	Abstract Environmental sound classification is one of the important issues in the audio recognition field. Compared with structured sounds such as speech and music, the time–frequency structure of environmental sounds is more complicated. In order to learn time and frequency features from Log-Mel spectrogram more effectively, a temporal-frequency attention based convolutional neural network model (TFCNN) is proposed in this paper. Firstly, an experiment that is used as motivation in proposed method is designed to verify the effect of a specific frequency band in the spectrogram on model classification. Secondly, two new attention mechanisms, temporal attention mechanism and frequency attention mechanism, are proposed. These mechanisms can focus on key frequency bands and semantic related time frames on the spectrogram to reduce the influence of background noise and irrelevant frequency bands. Then, a feature information complementarity is formed by combining these mechanisms to more accurately capture the critical time–frequency features. In such a way, the representation ability of the network model can be greatly improved. Finally, experiments on two public data sets, UrbanSound 8 K and ESC-50, demonstrate the effectiveness of the proposed method.
format	article
author	Wenjie Mu Bo Yin Xianqing Huang Jiali Xu Zehua Du
author_facet	Wenjie Mu Bo Yin Xianqing Huang Jiali Xu Zehua Du
author_sort	Wenjie Mu
title	Environmental sound classification using temporal-frequency attention based convolutional neural network
title_short	Environmental sound classification using temporal-frequency attention based convolutional neural network
title_full	Environmental sound classification using temporal-frequency attention based convolutional neural network
title_fullStr	Environmental sound classification using temporal-frequency attention based convolutional neural network
title_full_unstemmed	Environmental sound classification using temporal-frequency attention based convolutional neural network
title_sort	environmental sound classification using temporal-frequency attention based convolutional neural network
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/9ccc492d96474e4386fdec45cd0445a2
work_keys_str_mv	AT wenjiemu environmentalsoundclassificationusingtemporalfrequencyattentionbasedconvolutionalneuralnetwork AT boyin environmentalsoundclassificationusingtemporalfrequencyattentionbasedconvolutionalneuralnetwork AT xianqinghuang environmentalsoundclassificationusingtemporalfrequencyattentionbasedconvolutionalneuralnetwork AT jialixu environmentalsoundclassificationusingtemporalfrequencyattentionbasedconvolutionalneuralnetwork AT zehuadu environmentalsoundclassificationusingtemporalfrequencyattentionbasedconvolutionalneuralnetwork
_version_	1718442645290745857

Environmental sound classification using temporal-frequency attention based convolutional neural network

Ejemplares similares