Author
Eroğlu Erdem, Ç., Bozkurt, E., Erzin, E., Erdem, Tanju
Publication Date
2010
Publication Place
-
ACM
Subject
Affect recognition, Emotional speech classification, RANSAC, Data cleaning, Data pruning
Type
Document
Language
English
Digital
Yes
Manuscript
No
Library
Özyeğin University
Library Asset ID
978-1-4503-0170-1
Record ID
cedcd21c-080b-4f64-93a2-a0d5e81dba52
Library Location
Computer Science
Date
2010
Notes
Due to copyright restrictions, the access to the full text of this article is only available via subscription.
Sample Text
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.
DOI
10.1145/1877826.1877831
