@inproceedings{fahmi-etal-2020-speech,
title = "Speech-Emotion Detection in an {I}ndonesian Movie",
author = "Fahmi, Fahmi and
Jiwanggi, Meganingrum Arista and
Adriani, Mirna",
editor = "Beermann, Dorothee and
Besacier, Laurent and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources association",
url = "https://aclanthology.org/2020.sltu-1.26",
pages = "185--193",
abstract = "The growing demand to develop an automatic emotion recognition system for the Human-Computer Interaction field had pushed some research in speech emotion detection. Although it is growing, there is still little research about automatic speech emotion detection in Bahasa Indonesia. Another issue is the lack of standard corpus for this research area in Bahasa Indonesia. This study proposed several approaches to detect speech-emotion in the dialogs of an Indonesian movie by classifying them into 4 different emotion classes i.e. happiness, sadness, anger, and neutral. There are two different speech data representations used in this study i.e. statistical and temporal/sequence representations. This study used Artificial Neural Network (ANN), Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM) variation, word embedding, and also the hybrid of three to perform the classification task. The best accuracies given by one-vs-rest scenario for each emotion class with speech-transcript pairs using hybrid of non-temporal and embedding approach are 1) happiness: 76.31{\%}; 2) sadness: 86.46{\%}; 3) anger: 82.14{\%}; and 4) neutral: 68.51{\%}. The multiclass classification resulted in 64.66{\%} of precision, 66.79{\%} of recall, and 64.83{\%} of F1-score.",
language = "English",
ISBN = "979-10-95546-35-1",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fahmi-etal-2020-speech">
<titleInfo>
<title>Speech-Emotion Detection in an Indonesian Movie</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fahmi</namePart>
<namePart type="family">Fahmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meganingrum</namePart>
<namePart type="given">Arista</namePart>
<namePart type="family">Jiwanggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirna</namePart>
<namePart type="family">Adriani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dorothee</namePart>
<namePart type="family">Beermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-35-1</identifier>
</relatedItem>
<abstract>The growing demand to develop an automatic emotion recognition system for the Human-Computer Interaction field had pushed some research in speech emotion detection. Although it is growing, there is still little research about automatic speech emotion detection in Bahasa Indonesia. Another issue is the lack of standard corpus for this research area in Bahasa Indonesia. This study proposed several approaches to detect speech-emotion in the dialogs of an Indonesian movie by classifying them into 4 different emotion classes i.e. happiness, sadness, anger, and neutral. There are two different speech data representations used in this study i.e. statistical and temporal/sequence representations. This study used Artificial Neural Network (ANN), Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM) variation, word embedding, and also the hybrid of three to perform the classification task. The best accuracies given by one-vs-rest scenario for each emotion class with speech-transcript pairs using hybrid of non-temporal and embedding approach are 1) happiness: 76.31%; 2) sadness: 86.46%; 3) anger: 82.14%; and 4) neutral: 68.51%. The multiclass classification resulted in 64.66% of precision, 66.79% of recall, and 64.83% of F1-score.</abstract>
<identifier type="citekey">fahmi-etal-2020-speech</identifier>
<location>
<url>https://aclanthology.org/2020.sltu-1.26</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>185</start>
<end>193</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speech-Emotion Detection in an Indonesian Movie
%A Fahmi, Fahmi
%A Jiwanggi, Meganingrum Arista
%A Adriani, Mirna
%Y Beermann, Dorothee
%Y Besacier, Laurent
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)
%D 2020
%8 May
%I European Language Resources association
%C Marseille, France
%@ 979-10-95546-35-1
%G English
%F fahmi-etal-2020-speech
%X The growing demand to develop an automatic emotion recognition system for the Human-Computer Interaction field had pushed some research in speech emotion detection. Although it is growing, there is still little research about automatic speech emotion detection in Bahasa Indonesia. Another issue is the lack of standard corpus for this research area in Bahasa Indonesia. This study proposed several approaches to detect speech-emotion in the dialogs of an Indonesian movie by classifying them into 4 different emotion classes i.e. happiness, sadness, anger, and neutral. There are two different speech data representations used in this study i.e. statistical and temporal/sequence representations. This study used Artificial Neural Network (ANN), Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM) variation, word embedding, and also the hybrid of three to perform the classification task. The best accuracies given by one-vs-rest scenario for each emotion class with speech-transcript pairs using hybrid of non-temporal and embedding approach are 1) happiness: 76.31%; 2) sadness: 86.46%; 3) anger: 82.14%; and 4) neutral: 68.51%. The multiclass classification resulted in 64.66% of precision, 66.79% of recall, and 64.83% of F1-score.
%U https://aclanthology.org/2020.sltu-1.26
%P 185-193
Markdown (Informal)
[Speech-Emotion Detection in an Indonesian Movie](https://aclanthology.org/2020.sltu-1.26) (Fahmi et al., SLTU 2020)
ACL
- Fahmi Fahmi, Meganingrum Arista Jiwanggi, and Mirna Adriani. 2020. Speech-Emotion Detection in an Indonesian Movie. In Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL), pages 185–193, Marseille, France. European Language Resources association.