Efficient Arabic Emotion Recognition Using Deep Neural Networks

Yasser Hifny, Ahmed Ali

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Emotion recognition from speech signal based on deep learning is an active research area. Convolutional neural networks (CNNs) may be the dominant method in this area. In this paper, we implement two neural architectures to address this problem. The first architecture is an attention-based CNN-LSTM-DNN model. In this novel architecture, the convo-lutional layers extract salient features and the bi-directional long short-term memory (BLSTM) layers handle the sequential phenomena of the speech signal. This is followed by an attention layer, which extracts a summary vector that is fed to the fully connected dense layer (DNN), which finally connects to a softmax output layer. The second architecture is based on a deep CNN model. The results on an Arabic speech emotion recognition task show that our innovative approach can lead to significant improvements (2.2% absolute improvements) over a strong deep CNN baseline system. On the other hand, the deep CNN models are significantly faster than the attention based CNN-LSTM-DNN models in training and classification.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6710-6714
Number of pages5
ISBN (Electronic)9781479981311
DOIs
Publication statusPublished - 1 May 2019
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: 12 May 201917 May 2019

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May
ISSN (Print)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom
CityBrighton
Period12/5/1917/5/19

Fingerprint

Neural networks
Speech recognition
Deep neural networks

Keywords

  • and attention
  • bi-direction long short-term memory (BLSTM) networks
  • convolutional neural networks (CNN)
  • deep neural networks (DNN)
  • Speech emotion recognition

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Hifny, Y., & Ali, A. (2019). Efficient Arabic Emotion Recognition Using Deep Neural Networks. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 6710-6714). [8683632] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2019.8683632

Efficient Arabic Emotion Recognition Using Deep Neural Networks. / Hifny, Yasser; Ali, Ahmed.

2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 6710-6714 8683632 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hifny, Y & Ali, A 2019, Efficient Arabic Emotion Recognition Using Deep Neural Networks. in 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings., 8683632, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 6710-6714, 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, Brighton, United Kingdom, 12/5/19. https://doi.org/10.1109/ICASSP.2019.8683632
Hifny Y, Ali A. Efficient Arabic Emotion Recognition Using Deep Neural Networks. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 6710-6714. 8683632. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2019.8683632
Hifny, Yasser ; Ali, Ahmed. / Efficient Arabic Emotion Recognition Using Deep Neural Networks. 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 6710-6714 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{e6ce12fd809948689ee171b8b5aa15c0,
title = "Efficient Arabic Emotion Recognition Using Deep Neural Networks",
abstract = "Emotion recognition from speech signal based on deep learning is an active research area. Convolutional neural networks (CNNs) may be the dominant method in this area. In this paper, we implement two neural architectures to address this problem. The first architecture is an attention-based CNN-LSTM-DNN model. In this novel architecture, the convo-lutional layers extract salient features and the bi-directional long short-term memory (BLSTM) layers handle the sequential phenomena of the speech signal. This is followed by an attention layer, which extracts a summary vector that is fed to the fully connected dense layer (DNN), which finally connects to a softmax output layer. The second architecture is based on a deep CNN model. The results on an Arabic speech emotion recognition task show that our innovative approach can lead to significant improvements (2.2{\%} absolute improvements) over a strong deep CNN baseline system. On the other hand, the deep CNN models are significantly faster than the attention based CNN-LSTM-DNN models in training and classification.",
keywords = "and attention, bi-direction long short-term memory (BLSTM) networks, convolutional neural networks (CNN), deep neural networks (DNN), Speech emotion recognition",
author = "Yasser Hifny and Ahmed Ali",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/ICASSP.2019.8683632",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "6710--6714",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",

}

TY - GEN

T1 - Efficient Arabic Emotion Recognition Using Deep Neural Networks

AU - Hifny, Yasser

AU - Ali, Ahmed

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Emotion recognition from speech signal based on deep learning is an active research area. Convolutional neural networks (CNNs) may be the dominant method in this area. In this paper, we implement two neural architectures to address this problem. The first architecture is an attention-based CNN-LSTM-DNN model. In this novel architecture, the convo-lutional layers extract salient features and the bi-directional long short-term memory (BLSTM) layers handle the sequential phenomena of the speech signal. This is followed by an attention layer, which extracts a summary vector that is fed to the fully connected dense layer (DNN), which finally connects to a softmax output layer. The second architecture is based on a deep CNN model. The results on an Arabic speech emotion recognition task show that our innovative approach can lead to significant improvements (2.2% absolute improvements) over a strong deep CNN baseline system. On the other hand, the deep CNN models are significantly faster than the attention based CNN-LSTM-DNN models in training and classification.

AB - Emotion recognition from speech signal based on deep learning is an active research area. Convolutional neural networks (CNNs) may be the dominant method in this area. In this paper, we implement two neural architectures to address this problem. The first architecture is an attention-based CNN-LSTM-DNN model. In this novel architecture, the convo-lutional layers extract salient features and the bi-directional long short-term memory (BLSTM) layers handle the sequential phenomena of the speech signal. This is followed by an attention layer, which extracts a summary vector that is fed to the fully connected dense layer (DNN), which finally connects to a softmax output layer. The second architecture is based on a deep CNN model. The results on an Arabic speech emotion recognition task show that our innovative approach can lead to significant improvements (2.2% absolute improvements) over a strong deep CNN baseline system. On the other hand, the deep CNN models are significantly faster than the attention based CNN-LSTM-DNN models in training and classification.

KW - and attention

KW - bi-direction long short-term memory (BLSTM) networks

KW - convolutional neural networks (CNN)

KW - deep neural networks (DNN)

KW - Speech emotion recognition

UR - http://www.scopus.com/inward/record.url?scp=85069004881&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069004881&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2019.8683632

DO - 10.1109/ICASSP.2019.8683632

M3 - Conference contribution

AN - SCOPUS:85069004881

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 6710

EP - 6714

BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -