Next Article in Journal
Low-Cost Road-Surface Classification System Based on Self-Organizing Maps
Next Article in Special Issue
Multi-TALK: Multi-Microphone Cross-Tower Network for Jointly Suppressing Acoustic Echo and Background Noise
Previous Article in Journal
Generating Time-Series LAI Estimates of Maize Using Combined Methods Based on Multispectral UAV Observations and WOFOST Model
Previous Article in Special Issue
Incorporating Noise Robustness in Speech Command Recognition by Noise Augmentation of Training Data
 
 
Article

Impact of Feature Selection Algorithm on Speech Emotion Recognition Using Deep Convolutional Neural Network

1
Department of Computer Engineering, University of Engineering and Technology, Taxila 47050, Pakistan
2
Department of Software Engineering, University of Engineering and Technology, Taxila 47050, Pakistan
3
Machine Intelligence and Pattern Analysis Laboratory, Griffith University, Nathan QLD 4111, Australia
4
Department Electronics and Information Engineering, Korea University, Sejong 30019, Korea
5
Department of Information and Communication Engineering, Yeungnam University, Gyeongsan 38541, Korea
*
Authors to whom correspondence should be addressed.
Sensors 2020, 20(21), 6008; https://doi.org/10.3390/s20216008
Received: 19 September 2020 / Revised: 19 October 2020 / Accepted: 20 October 2020 / Published: 23 October 2020
(This article belongs to the Special Issue VOICE Sensors with Deep Learning)
Speech emotion recognition (SER) plays a significant role in human–machine interaction. Emotion recognition from speech and its precise classification is a challenging task because a machine is unable to understand its context. For an accurate emotion classification, emotionally relevant features must be extracted from the speech data. Traditionally, handcrafted features were used for emotional classification from speech signals; however, they are not efficient enough to accurately depict the emotional states of the speaker. In this study, the benefits of a deep convolutional neural network (DCNN) for SER are explored. For this purpose, a pretrained network is used to extract features from state-of-the-art speech emotional datasets. Subsequently, a correlation-based feature selection technique is applied to the extracted features to select the most appropriate and discriminative features for SER. For the classification of emotions, we utilize support vector machines, random forests, the k-nearest neighbors algorithm, and neural network classifiers. Experiments are performed for speaker-dependent and speaker-independent SER using four publicly available datasets: the Berlin Dataset of Emotional Speech (Emo-DB), Surrey Audio Visual Expressed Emotion (SAVEE), Interactive Emotional Dyadic Motion Capture (IEMOCAP), and the Ryerson Audio Visual Dataset of Emotional Speech and Song (RAVDESS). Our proposed method achieves an accuracy of 95.10% for Emo-DB, 82.10% for SAVEE, 83.80% for IEMOCAP, and 81.30% for RAVDESS, for speaker-dependent SER experiments. Moreover, our method yields the best results for speaker-independent SER with existing handcrafted features-based SER approaches. View Full-Text
Keywords: speech emotion recognition; deep convolutional neural network; correlation-based feature selection speech emotion recognition; deep convolutional neural network; correlation-based feature selection
Show Figures

Figure 1

MDPI and ACS Style

Farooq, M.; Hussain, F.; Baloch, N.K.; Raja, F.R.; Yu, H.; Zikria, Y.B. Impact of Feature Selection Algorithm on Speech Emotion Recognition Using Deep Convolutional Neural Network. Sensors 2020, 20, 6008. https://doi.org/10.3390/s20216008

AMA Style

Farooq M, Hussain F, Baloch NK, Raja FR, Yu H, Zikria YB. Impact of Feature Selection Algorithm on Speech Emotion Recognition Using Deep Convolutional Neural Network. Sensors. 2020; 20(21):6008. https://doi.org/10.3390/s20216008

Chicago/Turabian Style

Farooq, Misbah, Fawad Hussain, Naveed Khan Baloch, Fawad Riasat Raja, Heejung Yu, and Yousaf Bin Zikria. 2020. "Impact of Feature Selection Algorithm on Speech Emotion Recognition Using Deep Convolutional Neural Network" Sensors 20, no. 21: 6008. https://doi.org/10.3390/s20216008

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop