Skip to main navigation Skip to search Skip to main content

Towards more reality in the recognition of emotional speech

  • FBK-irst
  • Friedrich Alexander Universität Erlangen-Nürnberg

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

109 Scopus citations

Abstract

As automatic emotion recognition based on speech matures, new challenges can be faced. We therefore address the major aspects in view of potential applications in the field, to benchmark today's emotion recognition systems and bridge the gap between commercial interest and current performances: acted vs. spontaneous speech, realistic emotions, noise and microphone conditions, and speaker independence. Three different data-sets are used: the Berlin Emotional Speech Database, the Danish Emotional Speech Database, and the spontaneous AIBO Emotion Corpus. By using different feature types such as word- or turn-based statistics, manual versus forced alignment, and optimization techniques we show how to best cope with this demanding task and how noise addition or different microphone positions affect emotion recognition.

Original languageEnglish
Title of host publication2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
PagesIV941-IV944
DOIs
StatePublished - 2007
Event2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 - Honolulu, HI, United States
Duration: 15 Apr 200720 Apr 2007

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume4
ISSN (Print)1520-6149

Conference

Conference2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
Country/TerritoryUnited States
CityHonolulu, HI
Period15/04/0720/04/07

Keywords

  • Affective computing
  • Emotion recognition
  • Noise robustness
  • Spontaneous emotions

Fingerprint

Dive into the research topics of 'Towards more reality in the recognition of emotional speech'. Together they form a unique fingerprint.

Cite this