Skip to main navigation Skip to search Skip to main content

Improvement of emotion recognition from voice by separating of obstruents

  • Korea Advanced Institute of Science and Technology

Research output: Contribution to conferenceConference paperpeer-review

Abstract

Previous researchers in the area of emotion recognition have classified emotion from the whole voice. They did not consider that emotion features vary according to the phoneme. Hence, in the present work, we study the characteristics of phonemes in emotion features. Based on the results, we define the obstruents effect, which is a negative effect resulting from increased feature values. We then recognize emotion from the voice by separating obstruents rather than from the whole voice. By separating obstruents, we could improve the emotion recognition rate by about 4.3%.

Original languageEnglish
Title of host publicationProceedings - RO-MAN 2006 - The 15th IEEE International Symposium on Robot and Human Interactive Communication
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages564-568
Number of pages5
ISBN (Print)1424405653, 9781424405657
DOIs
StatePublished - 2006
Event15th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2006 - Hatfield, United Kingdom
Duration: 2006.09.62006.09.8

Publication series

NameProceedings - IEEE International Workshop on Robot and Human Interactive Communication
ISSN (Print)1944-9445
ISSN (Electronic)1944-9437

Conference

Conference15th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2006
Country/TerritoryUnited Kingdom
CityHatfield
Period06.09.606.09.8

Fingerprint

Dive into the research topics of 'Improvement of emotion recognition from voice by separating of obstruents'. Together they form a unique fingerprint.

Cite this