Deep Cross-Corpus Speech Emotion Recognition: Recent Advances and Perspectives

Automatic speech emotion recognition (SER) is a challenging component of human-computer interaction (HCI). Existing literatures mainly focus on evaluating the SER performance by means of training and testing on a single corpus with a single language setting. However, in many practical applications,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shiqing Zhang, Ruixin Liu, Xin Tao, Xiaoming Zhao
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	speech emotion recognition cross-corpus deep learning feature learning survey Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/7fd8069669d24c56bb97a67956552438
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7fd8069669d24c56bb97a67956552438
record_format	dspace
spelling	oai:doaj.org-article:7fd8069669d24c56bb97a679565524382021-12-01T12:33:50ZDeep Cross-Corpus Speech Emotion Recognition: Recent Advances and Perspectives1662-521810.3389/fnbot.2021.784514https://doaj.org/article/7fd8069669d24c56bb97a679565524382021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fnbot.2021.784514/fullhttps://doaj.org/toc/1662-5218Automatic speech emotion recognition (SER) is a challenging component of human-computer interaction (HCI). Existing literatures mainly focus on evaluating the SER performance by means of training and testing on a single corpus with a single language setting. However, in many practical applications, there are great differences between the training corpus and testing corpus. Due to the diversity of different speech emotional corpus or languages, most previous SER methods do not perform well when applied in real-world cross-corpus or cross-language scenarios. Inspired by the powerful feature learning ability of recently-emerged deep learning techniques, various advanced deep learning models have increasingly been adopted for cross-corpus SER. This paper aims to provide an up-to-date and comprehensive survey of cross-corpus SER, especially for various deep learning techniques associated with supervised, unsupervised and semi-supervised learning in this area. In addition, this paper also highlights different challenges and opportunities on cross-corpus SER tasks, and points out its future trends.Shiqing ZhangRuixin LiuRuixin LiuXin TaoXiaoming ZhaoFrontiers Media S.A.articlespeech emotion recognitioncross-corpusdeep learningfeature learningsurveyNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Neurorobotics, Vol 15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	speech emotion recognition cross-corpus deep learning feature learning survey Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	speech emotion recognition cross-corpus deep learning feature learning survey Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Shiqing Zhang Ruixin Liu Ruixin Liu Xin Tao Xiaoming Zhao Deep Cross-Corpus Speech Emotion Recognition: Recent Advances and Perspectives
description	Automatic speech emotion recognition (SER) is a challenging component of human-computer interaction (HCI). Existing literatures mainly focus on evaluating the SER performance by means of training and testing on a single corpus with a single language setting. However, in many practical applications, there are great differences between the training corpus and testing corpus. Due to the diversity of different speech emotional corpus or languages, most previous SER methods do not perform well when applied in real-world cross-corpus or cross-language scenarios. Inspired by the powerful feature learning ability of recently-emerged deep learning techniques, various advanced deep learning models have increasingly been adopted for cross-corpus SER. This paper aims to provide an up-to-date and comprehensive survey of cross-corpus SER, especially for various deep learning techniques associated with supervised, unsupervised and semi-supervised learning in this area. In addition, this paper also highlights different challenges and opportunities on cross-corpus SER tasks, and points out its future trends.
format	article
author	Shiqing Zhang Ruixin Liu Ruixin Liu Xin Tao Xiaoming Zhao
author_facet	Shiqing Zhang Ruixin Liu Ruixin Liu Xin Tao Xiaoming Zhao
author_sort	Shiqing Zhang
title	Deep Cross-Corpus Speech Emotion Recognition: Recent Advances and Perspectives
title_short	Deep Cross-Corpus Speech Emotion Recognition: Recent Advances and Perspectives
title_full	Deep Cross-Corpus Speech Emotion Recognition: Recent Advances and Perspectives
title_fullStr	Deep Cross-Corpus Speech Emotion Recognition: Recent Advances and Perspectives
title_full_unstemmed	Deep Cross-Corpus Speech Emotion Recognition: Recent Advances and Perspectives
title_sort	deep cross-corpus speech emotion recognition: recent advances and perspectives
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/7fd8069669d24c56bb97a67956552438
work_keys_str_mv	AT shiqingzhang deepcrosscorpusspeechemotionrecognitionrecentadvancesandperspectives AT ruixinliu deepcrosscorpusspeechemotionrecognitionrecentadvancesandperspectives AT ruixinliu deepcrosscorpusspeechemotionrecognitionrecentadvancesandperspectives AT xintao deepcrosscorpusspeechemotionrecognitionrecentadvancesandperspectives AT xiaomingzhao deepcrosscorpusspeechemotionrecognitionrecentadvancesandperspectives
_version_	1718405182541266944

Deep Cross-Corpus Speech Emotion Recognition: Recent Advances and Perspectives

Ejemplares similares