The Impact of Attention Mechanisms on Speech Emotion Recognition

Speech emotion recognition (SER) plays an important role in real-time applications of human-machine interaction. The Attention Mechanism is widely used to improve the performance of SER. However, the applicable rules of attention mechanism are not deeply discussed. This paper discussed the differenc...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shouyan Chen, Mingyan Zhang, Xiaofen Yang, Zhijia Zhao, Tao Zou, Xinqi Sun
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	artificial intelligence speech emotion recognition attention mechanism neural networks Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/9c6f6ffb5d894251a31c7913baf9b515
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9c6f6ffb5d894251a31c7913baf9b515
record_format	dspace
spelling	oai:doaj.org-article:9c6f6ffb5d894251a31c7913baf9b5152021-11-25T18:57:11ZThe Impact of Attention Mechanisms on Speech Emotion Recognition10.3390/s212275301424-8220https://doaj.org/article/9c6f6ffb5d894251a31c7913baf9b5152021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7530https://doaj.org/toc/1424-8220Speech emotion recognition (SER) plays an important role in real-time applications of human-machine interaction. The Attention Mechanism is widely used to improve the performance of SER. However, the applicable rules of attention mechanism are not deeply discussed. This paper discussed the difference between Global-Attention and Self-Attention and explored their applicable rules to SER classification construction. The experimental results show that the Global-Attention can improve the accuracy of the sequential model, while the Self-Attention can improve the accuracy of the parallel model when conducting the model with the CNN and the LSTM. With this knowledge, a classifier (CNN-LSTM×2+Global-Attention model) for SER is proposed. The experiments result show that it could achieve an accuracy of 85.427% on the EMO-DB dataset.Shouyan ChenMingyan ZhangXiaofen YangZhijia ZhaoTao ZouXinqi SunMDPI AGarticleartificial intelligencespeech emotion recognitionattention mechanismneural networksChemical technologyTP1-1185ENSensors, Vol 21, Iss 7530, p 7530 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	artificial intelligence speech emotion recognition attention mechanism neural networks Chemical technology TP1-1185
spellingShingle	artificial intelligence speech emotion recognition attention mechanism neural networks Chemical technology TP1-1185 Shouyan Chen Mingyan Zhang Xiaofen Yang Zhijia Zhao Tao Zou Xinqi Sun The Impact of Attention Mechanisms on Speech Emotion Recognition
description	Speech emotion recognition (SER) plays an important role in real-time applications of human-machine interaction. The Attention Mechanism is widely used to improve the performance of SER. However, the applicable rules of attention mechanism are not deeply discussed. This paper discussed the difference between Global-Attention and Self-Attention and explored their applicable rules to SER classification construction. The experimental results show that the Global-Attention can improve the accuracy of the sequential model, while the Self-Attention can improve the accuracy of the parallel model when conducting the model with the CNN and the LSTM. With this knowledge, a classifier (CNN-LSTM×2+Global-Attention model) for SER is proposed. The experiments result show that it could achieve an accuracy of 85.427% on the EMO-DB dataset.
format	article
author	Shouyan Chen Mingyan Zhang Xiaofen Yang Zhijia Zhao Tao Zou Xinqi Sun
author_facet	Shouyan Chen Mingyan Zhang Xiaofen Yang Zhijia Zhao Tao Zou Xinqi Sun
author_sort	Shouyan Chen
title	The Impact of Attention Mechanisms on Speech Emotion Recognition
title_short	The Impact of Attention Mechanisms on Speech Emotion Recognition
title_full	The Impact of Attention Mechanisms on Speech Emotion Recognition
title_fullStr	The Impact of Attention Mechanisms on Speech Emotion Recognition
title_full_unstemmed	The Impact of Attention Mechanisms on Speech Emotion Recognition
title_sort	impact of attention mechanisms on speech emotion recognition
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/9c6f6ffb5d894251a31c7913baf9b515
work_keys_str_mv	AT shouyanchen theimpactofattentionmechanismsonspeechemotionrecognition AT mingyanzhang theimpactofattentionmechanismsonspeechemotionrecognition AT xiaofenyang theimpactofattentionmechanismsonspeechemotionrecognition AT zhijiazhao theimpactofattentionmechanismsonspeechemotionrecognition AT taozou theimpactofattentionmechanismsonspeechemotionrecognition AT xinqisun theimpactofattentionmechanismsonspeechemotionrecognition AT shouyanchen impactofattentionmechanismsonspeechemotionrecognition AT mingyanzhang impactofattentionmechanismsonspeechemotionrecognition AT xiaofenyang impactofattentionmechanismsonspeechemotionrecognition AT zhijiazhao impactofattentionmechanismsonspeechemotionrecognition AT taozou impactofattentionmechanismsonspeechemotionrecognition AT xinqisun impactofattentionmechanismsonspeechemotionrecognition
_version_	1718410543069396992

The Impact of Attention Mechanisms on Speech Emotion Recognition

Ejemplares similares