Emotion estimation by joint facial expression and speech tonality using evolutionary deep learning structures

Chih Che Chung, Wei Ting Lin, Rong Zhang, Kai Wen Liang, Pao Chi Chang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

This work proposes an emotion recognition system by adopting facial expression and speech tonality on deep learning networks. Both convolutional neural networks and long short term memory networks are used for feature training. The two features can be trained together to acquire higher accuracy. Moreover, Structure Evolution which is inspired by the Genetic Algorithm is added to optimize the parameters in the model. The experimental results show the joint model optimized by Structure Evolution surpasses the single model by at least 10% and outperforms the state-of-the-art work over 1%.

Original languageEnglish
Title of host publication2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages221-224
Number of pages4
ISBN (Electronic)9781728135755
DOIs
StatePublished - Oct 2019
Event8th IEEE Global Conference on Consumer Electronics, GCCE 2019 - Osaka, Japan
Duration: 15 Oct 201918 Oct 2019

Publication series

Name2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019

Conference

Conference8th IEEE Global Conference on Consumer Electronics, GCCE 2019
Country/TerritoryJapan
CityOsaka
Period15/10/1918/10/19

Keywords

  • Deep learning
  • Emotion estimation
  • Facial expression
  • Speech
  • Structure Evolution

Fingerprint

Dive into the research topics of 'Emotion estimation by joint facial expression and speech tonality using evolutionary deep learning structures'. Together they form a unique fingerprint.

Cite this