Speech Emotion Recognition Using Deep Learning Techniques: A Review

Ruhul Amin Khalil; Edward Jones; Mohammad Inayatullah Babar; Tariqullah Jan; Mohammad Haseeb Zafar; Thamer Alhussain

doi:10.1109/ACCESS.2019.2936124

Speech Emotion Recognition Using Deep Learning Techniques: A Review

Ruhul Amin Khalil^*, Edward Jones, Mohammad Inayatullah Babar, Tariqullah Jan, Mohammad Haseeb Zafar, Thamer Alhussain

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

412 Citations (Scopus)

Abstract

Emotion recognition from speech signals is an important but challenging component of Human-Computer Interaction (HCI). In the literature of speech emotion recognition (SER), many techniques have been utilized to extract emotions from signals, including many well-established speech analysis and classification techniques. Deep Learning techniques have been recently proposed as an alternative to traditional techniques in SER. This paper presents an overview of Deep Learning techniques and discusses some recent literature where these methods are utilized for speech-based emotion recognition. The review covers databases used, emotions extracted, contributions made toward speech emotion recognition and limitations related to it.

Original language	English
Article number	8805181
Pages (from-to)	117327-117345
Number of pages	19
Journal	IEEE Access
Volume	7
DOIs	https://doi.org/10.1109/ACCESS.2019.2936124
Publication status	Published - 19 Aug 2019
Externally published	Yes

Keywords

Speech emotion recognition
convolutional neural network
deep Boltzmann machine
deep belief network
deep learning
deep neural network
recurrent neural network

Access to Document

10.1109/ACCESS.2019.2936124

Cite this

@article{bb53ede9e4564ad2b0875d4502128f46,

title = "Speech Emotion Recognition Using Deep Learning Techniques: A Review",

abstract = "Emotion recognition from speech signals is an important but challenging component of Human-Computer Interaction (HCI). In the literature of speech emotion recognition (SER), many techniques have been utilized to extract emotions from signals, including many well-established speech analysis and classification techniques. Deep Learning techniques have been recently proposed as an alternative to traditional techniques in SER. This paper presents an overview of Deep Learning techniques and discusses some recent literature where these methods are utilized for speech-based emotion recognition. The review covers databases used, emotions extracted, contributions made toward speech emotion recognition and limitations related to it.",

keywords = "Speech emotion recognition, convolutional neural network, deep Boltzmann machine, deep belief network, deep learning, deep neural network, recurrent neural network",

author = "Khalil, {Ruhul Amin} and Edward Jones and Babar, {Mohammad Inayatullah} and Tariqullah Jan and Zafar, {Mohammad Haseeb} and Thamer Alhussain",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2019",

month = aug,

day = "19",

doi = "10.1109/ACCESS.2019.2936124",

language = "English",

volume = "7",

pages = "117327--117345",

journal = "IEEE Access",

issn = "2169-3536",

}

TY - JOUR

T1 - Speech Emotion Recognition Using Deep Learning Techniques

T2 - A Review

AU - Khalil, Ruhul Amin

AU - Jones, Edward

AU - Babar, Mohammad Inayatullah

AU - Jan, Tariqullah

AU - Zafar, Mohammad Haseeb

AU - Alhussain, Thamer

PY - 2019/8/19

Y1 - 2019/8/19

N2 - Emotion recognition from speech signals is an important but challenging component of Human-Computer Interaction (HCI). In the literature of speech emotion recognition (SER), many techniques have been utilized to extract emotions from signals, including many well-established speech analysis and classification techniques. Deep Learning techniques have been recently proposed as an alternative to traditional techniques in SER. This paper presents an overview of Deep Learning techniques and discusses some recent literature where these methods are utilized for speech-based emotion recognition. The review covers databases used, emotions extracted, contributions made toward speech emotion recognition and limitations related to it.

AB - Emotion recognition from speech signals is an important but challenging component of Human-Computer Interaction (HCI). In the literature of speech emotion recognition (SER), many techniques have been utilized to extract emotions from signals, including many well-established speech analysis and classification techniques. Deep Learning techniques have been recently proposed as an alternative to traditional techniques in SER. This paper presents an overview of Deep Learning techniques and discusses some recent literature where these methods are utilized for speech-based emotion recognition. The review covers databases used, emotions extracted, contributions made toward speech emotion recognition and limitations related to it.

KW - Speech emotion recognition

KW - convolutional neural network

KW - deep Boltzmann machine

KW - deep belief network

KW - deep learning

KW - deep neural network

KW - recurrent neural network

UR - http://www.scopus.com/inward/record.url?scp=85097333678&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2936124

DO - 10.1109/ACCESS.2019.2936124

M3 - Article

AN - SCOPUS:85097333678

SN - 2169-3536

VL - 7

SP - 117327

EP - 117345

JO - IEEE Access

JF - IEEE Access

M1 - 8805181

ER -

Speech Emotion Recognition Using Deep Learning Techniques: A Review

Abstract

Keywords

Access to Document

Other files and links

Cite this