RANSAC-based training data selection for emotion recognition from spontaneous speech
dc.contributor.author | Eroğlu Erdem, Ç. | |
dc.contributor.author | Bozkurt, E. | |
dc.contributor.author | Erzin, E. | |
dc.contributor.author | Erdem, Tanju | |
dc.date.accessioned | 2016-02-11T14:25:41Z | |
dc.date.available | 2016-02-11T14:25:41Z | |
dc.date.issued | 2010 | |
dc.identifier.isbn | 978-1-4503-0170-1 | |
dc.identifier.uri | http://hdl.handle.net/10679/2048 | |
dc.identifier.uri | http://dl.acm.org/citation.cfm?id=1877831 | |
dc.description | Due to copyright restrictions, the access to the full text of this article is only available via subscription. | |
dc.description.abstract | Training datasets containing spontaneous emotional expressions are often imperfect due the ambiguities and difficulties of labeling such data by human observers. In this paper, we present a Random Sampling Consensus (RANSAC) based training approach for the problem of emotion recognition from spontaneous speech recordings. Our motivation is to insert a data cleaning process to the training phase of the Hidden Markov Models (HMMs) for the purpose of removing some suspicious instances of labels that may exist in the training dataset. Our experiments using HMMs with various number of states and Gaussian mixtures per state indicate that utilization of RANSAC in the training phase provides an improvement of up to 2.84% in the unweighted recall rates on the test set. This improvement in the accuracy of the classifier is shown to be statistically significant using McNemar’s test. | |
dc.description.sponsorship | TÜBİTAK ; Bahçeşehir University Research Fund | |
dc.language.iso | eng | en_US |
dc.publisher | ACM | |
dc.relation | info:turkey/grantAgreement/TUBITAK/110E056 | |
dc.relation | info:turkey/grantAgreement/TUBITAK/106E201 | |
dc.relation.ispartof | AFFINE '10 Proceedings of the 3rd international workshop on Affective interaction in natural environments | |
dc.rights | restrictedAccess | |
dc.title | RANSAC-based training data selection for emotion recognition from spontaneous speech | en_US |
dc.type | Conference paper | en_US |
dc.peerreviewed | yes | |
dc.publicationstatus | published | en_US |
dc.contributor.department | Özyeğin University | |
dc.contributor.authorID | (ORCID 0000-0002-8841-1642 & YÖK ID 45777) Erdem, Tanju | |
dc.contributor.ozuauthor | Erdem, Tanju | |
dc.identifier.startpage | 9 | |
dc.identifier.endpage | 14 | |
dc.identifier.doi | 10.1145/1877826.1877831 | |
dc.subject.keywords | Affect recognition | |
dc.subject.keywords | Emotional speech classification | |
dc.subject.keywords | RANSAC | |
dc.subject.keywords | Data cleaning | |
dc.subject.keywords | Data pruning | |
dc.identifier.scopus | SCOPUS:2-s2.0-78650482962 | |
dc.contributor.authorMale | 1 | |
dc.relation.publicationcategory | Conference Paper - International - Institutional Academic Staff |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |
This item appears in the following Collection(s)
Share this page