Towards a Comprehensive Approach to Complex Emotion Detection: Utilizing Facial and Speech Inputs in a 2D Matrix

Jenish Savaliya, Narumon Jadram, Peeraya Sripian, Midori Sugaya

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This study presents a novel approach to detecting complex emotions by integrating facial and speech cues using a hierarchical, rule-based system. Facial expressions have been evaluated using a Convolutional Neural Network (CNN) trained on the FER2013 dataset, whereas speech cues were processed using a Multi-Layer Perceptron (MLP) trained on the RAVDESS and TESS datasets. The integration mechanism employs a predefined 2D Emotion Matrix, mapping combinations of basic emotions to complex emotions. Phase 1 demonstrates the system's capability to detect and integrate emotions effectively, with Phase 2 focusing on validation and dataset expansion using participant feedback and generative AI. Validation with IEMOCAP and experimental datasets highlights the system’s robustness in recognizing complex emotional states. This research aims to address the limitations of existing emotion detection models by contributing to the creation of comprehensive datasets and systems for complex emotion recognition.

Original languageEnglish
Title of host publicationDistributed, Ambient and Pervasive Interactions - 13th International Conference, DAPI 2025, Held as Part of the 27th HCI International Conference, HCII 2025, Proceedings
EditorsNorbert A. Streitz, Shinichi Konomi
PublisherSpringer Science and Business Media Deutschland GmbH
Pages130-144
Number of pages15
ISBN (Print)9783031929762
DOIs
Publication statusPublished - 2025
Event13th International Conference on Distributed, Ambient and Pervasive Interactions, DAPI 2025, held as part of the 27th HCI International Conference, HCII 2025 - Gothenburg, Sweden
Duration: 2025 Jun 222025 Jun 27

Publication series

NameLecture Notes in Computer Science
Volume15802 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference13th International Conference on Distributed, Ambient and Pervasive Interactions, DAPI 2025, held as part of the 27th HCI International Conference, HCII 2025
Country/TerritorySweden
CityGothenburg
Period25/6/2225/6/27

Keywords

  • 2D Emotion Matrix
  • complex emotion detection
  • dataset validation
  • facial expressions
  • generative AI
  • neural networks
  • speech cues

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Towards a Comprehensive Approach to Complex Emotion Detection: Utilizing Facial and Speech Inputs in a 2D Matrix'. Together they form a unique fingerprint.

Cite this