Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/19335
Title: | A Self-Attentive Emotion Recognition Network | Authors: | Partaourides, Harris Papadamou, Kostantinos Kourtellis, Nicolas Leontiades, Ilias Chatzis, Sotirios P. |
Major Field of Science: | Natural Sciences | Field Category: | Computer and Information Sciences | Keywords: | Deep Learning;Emotion Recognition;Self-Attention | Issue Date: | 14-May-2020 | Source: | IEEE International Conference on Acoustics, Speech and Signal Processing, 4-8 May 2020, Barcelona, Spain | Conference: | IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | Abstract: | Attention networks constitute the state-of-the-art paradigm for capturing long temporal dynamics. This paper examines the efficacy of this paradigm in the challenging task of emotion recognition in dyadic conversations. In this work, we introduce a novel attention mechanism capable of inferring the immensity of the effect of each past utterance on the current speaker emotional state. The proposed self-attention network captures the correlation patterns among consecutive encoder network states, thus enabling the robust and effective modeling of temporal dynamics over arbitrary long temporal horizons. We exhibit the effectiveness of our approach considering the challenging IEMOCAP benchmark. We show that, our devised methodology outperforms state-of-the-art alternatives and commonly used approaches, giving rise to promising new research directions in the context of Online Social Network (OSN) analysis tasks. | URI: | https://hdl.handle.net/20.500.14279/19335 | ISBN: | 978-1-5090-6631-5 | DOI: | 10.1109/ICASSP40776.2020.9054762 | Rights: | © IEEE. | Type: | Conference Papers | Affiliation : | Cyprus University of Technology Telefonica Research Samsung |
Publication Type: | Peer Reviewed |
Appears in Collections: | Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation |
CORE Recommender
SCOPUSTM
Citations
5
4
checked on Nov 6, 2023
Page view(s) 5
309
Last Week
1
1
Last month
6
6
checked on Nov 21, 2024
Google ScholarTM
Check
Altmetric
This item is licensed under a Creative Commons License