Sayisal ses sinyallerinden duygu algilama

Translated title of the contribution: Emotion recognition from audio

Samet Yaslan*, Bilge Günsel

*Corresponding author for this work

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

Abstract

This paper presents a system for emotion recognition from audio. The emotion recognition problem is described as a four class classification problem in a 17 dimensional feture space. Currently, considered emotions are: Anger, happiness, sadness and unemotional. A SVM classifier with Gaussian RBF kernel is used for the classification. Experimental results obtained on a database that contains 11 different sentences recorded by 11 different speakers in four different emotions, are reported. It is shown that the developed system enables classifying four emotions with higher than 70% accuracy, with a false alarm ratio is less than 30%.

Translated title of the contributionEmotion recognition from audio
Original languageTurkish
Title of host publicationProceedings of the IEEE 13th Signal Processing and Communications Applications Conference, SIU 2005
Pages656-659
Number of pages4
DOIs
Publication statusPublished - 2005
EventIEEE 13th Signal Processing and Communications Applications Conference, SIU 2005 - Kayseri, Turkey
Duration: 16 May 200518 May 2005

Publication series

NameProceedings of the IEEE 13th Signal Processing and Communications Applications Conference, SIU 2005
Volume2005

Conference

ConferenceIEEE 13th Signal Processing and Communications Applications Conference, SIU 2005
Country/TerritoryTurkey
CityKayseri
Period16/05/0518/05/05

Fingerprint

Dive into the research topics of 'Emotion recognition from audio'. Together they form a unique fingerprint.

Cite this