Classifying emotions in speech: A comparison of methods

Noam Amir, Ori Kerret, Dimitry Karlinski

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

Abstract

A number of recent studies have attempted classification of emotional speech using various methods. In this paper we compare the performance of two algorithms: A classification algorithm based on euclidean distances, and a classification algorithm based on the use of neural networks. Both perform the classification using an identical feature set, on a database of emotional speech which has been validated through subjective listening tests.

Original languageEnglish
Title of host publicationEUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology
EditorsBorge Lindberg, Henrik Benner, Paul Dalsgaard, Zheng-Hua Tan
PublisherInternational Speech Communication Association
Pages127-130
Number of pages4
ISBN (Electronic)8790834100, 9788790834104
StatePublished - 2001
Externally publishedYes
Event7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001 - Aalborg, Denmark
Duration: 3 Sep 20017 Sep 2001

Publication series

NameEUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

Conference

Conference7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001
Country/TerritoryDenmark
CityAalborg
Period3/09/017/09/01

Fingerprint

Dive into the research topics of 'Classifying emotions in speech: A comparison of methods'. Together they form a unique fingerprint.

Cite this