JAIST Repository >
School of Information Science >
Articles >
Journal Articles >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/16961

Title: Continuous Audiovisual Emotion Recognition Using Feature Selection and LSTM
Authors: Elbarougy, Reda
Atmaja, Bagus Tris
Akagi, Masato
Keywords: continuous emotion recognition
audiovisual
feature selection
LSTM
Issue Date: 2020-11-01
Publisher: Research Institute of Signal Processing Japan
Magazine name: Journal of Signal Processing
Volume: 24
Number: 6
Start page: 229
End page: 235
DOI: 10.2299/jsp.24.229
Abstract: Speech and visual information are the most dominant modalities for a human to perceive emotion. A method of recognizing human emotion from these modalities is proposed by utilizing feature selection and long short-term memory (LSTM) neural networks. A feature selection method based on support vector regression is used to select the relevant features among thousands of features extended from speech and video features via bag-of-X-words. The LSTM neural networks then are trained using a number of selected features and also separately optimized for every emotion dimension. Instead of utterance-level emotion recognition, time-frame-based processing is performed to enable continuous emotion recognition using a database labeled for each time frame. Experimental results reveal that a system with feature selection is more effective for predicting emotion dimensions for a single language than the baseline system without feature selection. The performance is measured in terms of the concordance correlation coefficient obtained by averaging the valence, arousal, and liking dimensions.
Rights: Copyright (C) 2020 Research Institute of Signal Processing Japan. Reda Elbarougy, Bagus Tris Atmaja and Masato Akagi, Journal of Signal Processing, 24(6), 2020, pp.229-235. http://dx.doi.org/10.2299/jsp.24.229
URI: http://hdl.handle.net/10119/16961
Material Type: publisher
Appears in Collections:b10-1. 雑誌掲載論文 (Journal Articles)

Files in This Item:

File Description SizeFormat
3359.pdf2751KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, JAIST (ir-sys[at]ml.jaist.ac.jp)