Emotional speech classification with prosodic prameters by using neural networks

H. Sato, Y. Mitsukura, M. Fukumi, N. Akamatsu

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

9 Citations (Scopus)

Abstract

Interestingly, in order to achieve a new Human Interface such that digital computers can deal with the KASEI information, the study of the KANSEI information processing recently has been approached. In this paper, we propose a new classification method of emotional speech by analyzing feature parameters obtained from the emotional speech and by learning them using neural networks, which is regarded as a KANSEI information processing. In the present research, KANSEI information is usually human emotion. The emotion is classified broadly into four patterns such as neutral, anger, sad and joy. The pitch as one of feature parameters governs voice modulation, and can be sensitive to change of emotion. The pitch is extracted from each emotional speech by the cepstrum method. Input values of neural networks (NNs) are then emotional pitch patterns, which are time-varying. It is shown that NNs can achieve classification of emotion by learning each emotional pitch pattern by means of computer simulations.

Original languageEnglish
Title of host publicationANZIIS 2001 - Proceedings of the 7th Australian and New Zealand Intelligent Information Systems Conference
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages395-398
Number of pages4
ISBN (Electronic)1740520610, 9781740520614
DOIs
Publication statusPublished - 2001 Jan 1
Externally publishedYes
Event7th Australian and New Zealand Intelligent Information Systems Conference, ANZIIS 2001 - Perth, Australia
Duration: 2001 Nov 182001 Nov 21

Publication series

NameANZIIS 2001 - Proceedings of the 7th Australian and New Zealand Intelligent Information Systems Conference

Other

Other7th Australian and New Zealand Intelligent Information Systems Conference, ANZIIS 2001
CountryAustralia
CityPerth
Period01/11/1801/11/21

ASJC Scopus subject areas

  • Information Systems
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Emotional speech classification with prosodic prameters by using neural networks'. Together they form a unique fingerprint.

  • Cite this

    Sato, H., Mitsukura, Y., Fukumi, M., & Akamatsu, N. (2001). Emotional speech classification with prosodic prameters by using neural networks. In ANZIIS 2001 - Proceedings of the 7th Australian and New Zealand Intelligent Information Systems Conference (pp. 395-398). [974111] (ANZIIS 2001 - Proceedings of the 7th Australian and New Zealand Intelligent Information Systems Conference). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ANZIIS.2001.974111