Shirian, Amir and Guha, Tanaya (2021) Compact graph architecture for speech emotion recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Ontario, Canada, 6-11 Jun 2021. Published in: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) doi:10.1109/ICASSP39728.2021.9413876 ISSN 2379-190X.

Preview

PDF WRAP-compact-graph-architecture-speech-emotion-recognition-Guha-2021.pdf - Accepted Version - Requires a PDF viewer. Download (1218Kb) | Preview

Request Changes to record.

Abstract

We propose a deep graph approach to address the task of speech emotion recognition. A compact, efficient and scalable way to represent data is in the form of graphs. Following the theory of graph signal processing, we propose to model speech signal as a cycle graph or a line graph. Such graph structure enables us to construct a Graph Convolution Network (GCN)-based architecture that can perform an accurate graph convolution in contrast to the approximate convolution used in standard GCNs. We evaluated the performance of our model for speech emotion recognition on the popular IEMOCAP and MSP-IMPROV databases. Our model outperforms standard GCN and other relevant deep graph architectures indicating the effectiveness of our approach. When compared with existing speech emotion recognition methods, our model achieves comparable performance to the state-of-the-art with significantly fewer learnable parameters (~30K) indicating its applicability in resource-constrained devices. Our code is available at /github.com/AmirSh15/Compact_SER.

Item Type:	Conference Item (Paper)
Subjects:	P Language and Literature > P Philology. Linguistics Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Faculty of Science, Engineering and Medicine > Science > Computer Science
Library of Congress Subject Headings (LCSH):	Natural language processing (Computer science) , Speech processing systems, Automatic speech recognition, Computational linguistics , Emotions -- Data processing, Graphy theory, Neural networks (Computer science), Signal processing
Journal or Publication Title:	ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher:	IEEE
ISSN:	2379-190X
Official Date:	13 May 2021
Dates:	Date Event 13 May 2021 Published 30 January 2021 Accepted
DOI:	10.1109/ICASSP39728.2021.9413876
Status:	Peer Reviewed
Publication Status:	Published
Reuse Statement (publisher, data, author rights):	© Copyright 2021 IEEE. Published in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), scheduled for 6-11 June 2021 in Toronto, Ontario, Canada. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the IEEE. Contact: Manager, Copyrights and Permissions / IEEE Service Center / 445 Hoes Lane / P.O. Box 1331 / Piscataway, NJ 08855-1331, USA. Telephone: + Intl. 908-562-3966.
Access rights to Published version:	Restricted or Subscription Access
Date of first compliant deposit:	17 March 2021
Date of first compliant Open Access:	19 March 2021
Is Part Of:	1
Conference Paper Type:	Paper
Title of Event:	IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Type of Event:	Conference
Location of Event:	Toronto, Ontario, Canada
Date(s) of Event:	6-11 Jun 2021
Related URLs:	Publisher

Request changes or add full text files to a record

Repository staff actions (login required)

View Item

Downloads