Παρακαλώ χρησιμοποιήστε αυτό το αναγνωριστικό για να παραπέμψετε ή να δημιουργήσετε σύνδεσμο προς αυτό το τεκμήριο: https://hdl.handle.net/20.500.14279/19335
Τίτλος: A Self-Attentive Emotion Recognition Network
Συγγραφείς: Partaourides, Harris 
Papadamou, Kostantinos 
Kourtellis, Nicolas 
Leontiades, Ilias 
Chatzis, Sotirios P. 
Major Field of Science: Natural Sciences
Field Category: Computer and Information Sciences
Λέξεις-κλειδιά: Deep Learning;Emotion Recognition;Self-Attention
Ημερομηνία Έκδοσης: 14-Μαΐ-2020
Πηγή: 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) 
Περίληψη: 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
Εμφανίζεται στις συλλογές:Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation

CORE Recommender
Δείξε την πλήρη περιγραφή του τεκμηρίου

SCOPUSTM   
Citations 5

4
checked on 6 Νοε 2023

Page view(s) 5

307
Last Week
0
Last month
6
checked on 6 Νοε 2024

Google ScholarTM

Check

Altmetric


Αυτό το τεκμήριο προστατεύεται από άδεια Άδεια Creative Commons Creative Commons