Sorry, you need to enable JavaScript to visit this website.

A Self-Attentive Emotion Recognition Network

Citation Author(s):
Harris Partaourides, Kostantinos Papadamou, Nicolas Kourtellis, Ilias Leontiades, Sotirios Chatzis
Submitted by:
Harris Partaourides
Last updated:
13 February 2020 - 2:28pm
Document Type:
Poster
Document Year:
2020
Event:
Presenters Name:
Harris Partaourides
Paper Code:
3235

Abstract 

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.

up
0 users have voted:

Dataset Files

Poster__A_Self_Attentive_Emotion_Recognition_Network.pdf

(104)