@inproceedings{mori-etal-2016-accuracy,
title = "Accuracy of Automatic Cross-Corpus Emotion Labeling for Conversational Speech Corpus Commonization",
author = "Mori, Hiroki and
Nagaoka, Atsushi and
Arimoto, Yoshiko",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1634",
pages = "4019--4023",
abstract = "There exists a major incompatibility in emotion labeling framework among emotional speech corpora, that is, category-based and dimension-based. Commonizing these requires inter-corpus emotion labeling according to both frameworks, but doing this by human annotators is too costly for most cases. This paper examines the possibility of automatic cross-corpus emotion labeling. In order to evaluate the effectiveness of the automatic labeling, a comprehensive emotion annotation for two conversational corpora, UUDB and OGVC, was performed. With a state-of-the-art machine learning technique, dimensional and categorical emotion estimation models were trained and tested against the two corpora. For the emotion dimension estimation, the automatic cross-corpus emotion labeling for the different corpus was effective for the dimensions of aroused-sleepy, dominant-submissive and interested-indifferent, showing only slight performance degradation against the result for the same corpus. On the other hand, the performance for the emotion category estimation was not sufficient.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mori-etal-2016-accuracy">
<titleInfo>
<title>Accuracy of Automatic Cross-Corpus Emotion Labeling for Conversational Speech Corpus Commonization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Mori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsushi</namePart>
<namePart type="family">Nagaoka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshiko</namePart>
<namePart type="family">Arimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There exists a major incompatibility in emotion labeling framework among emotional speech corpora, that is, category-based and dimension-based. Commonizing these requires inter-corpus emotion labeling according to both frameworks, but doing this by human annotators is too costly for most cases. This paper examines the possibility of automatic cross-corpus emotion labeling. In order to evaluate the effectiveness of the automatic labeling, a comprehensive emotion annotation for two conversational corpora, UUDB and OGVC, was performed. With a state-of-the-art machine learning technique, dimensional and categorical emotion estimation models were trained and tested against the two corpora. For the emotion dimension estimation, the automatic cross-corpus emotion labeling for the different corpus was effective for the dimensions of aroused-sleepy, dominant-submissive and interested-indifferent, showing only slight performance degradation against the result for the same corpus. On the other hand, the performance for the emotion category estimation was not sufficient.</abstract>
<identifier type="citekey">mori-etal-2016-accuracy</identifier>
<location>
<url>https://aclanthology.org/L16-1634</url>
</location>
<part>
<date>2016-may</date>
<extent unit="page">
<start>4019</start>
<end>4023</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Accuracy of Automatic Cross-Corpus Emotion Labeling for Conversational Speech Corpus Commonization
%A Mori, Hiroki
%A Nagaoka, Atsushi
%A Arimoto, Yoshiko
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 may
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F mori-etal-2016-accuracy
%X There exists a major incompatibility in emotion labeling framework among emotional speech corpora, that is, category-based and dimension-based. Commonizing these requires inter-corpus emotion labeling according to both frameworks, but doing this by human annotators is too costly for most cases. This paper examines the possibility of automatic cross-corpus emotion labeling. In order to evaluate the effectiveness of the automatic labeling, a comprehensive emotion annotation for two conversational corpora, UUDB and OGVC, was performed. With a state-of-the-art machine learning technique, dimensional and categorical emotion estimation models were trained and tested against the two corpora. For the emotion dimension estimation, the automatic cross-corpus emotion labeling for the different corpus was effective for the dimensions of aroused-sleepy, dominant-submissive and interested-indifferent, showing only slight performance degradation against the result for the same corpus. On the other hand, the performance for the emotion category estimation was not sufficient.
%U https://aclanthology.org/L16-1634
%P 4019-4023
Markdown (Informal)
[Accuracy of Automatic Cross-Corpus Emotion Labeling for Conversational Speech Corpus Commonization](https://aclanthology.org/L16-1634) (Mori et al., LREC 2016)
ACL