@inproceedings{arroniz-kubler-2023-question,
title = "Was That a Question? Automatic Classification of Discourse Meaning in {S}panish",
author = {Arr{\'o}niz, Santiago and
K{\"u}bler, Sandra},
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ranlp-1.15",
pages = "132--142",
abstract = "This paper examines the effectiveness of different feature representations of audio data in accurately classifying discourse meaning in Spanish. The task involves determining whether an utterance is a declarative sentence, an interrogative, an imperative, etc. We explore how pitch contour can be represented for a discourse-meaning classification task, employing three different audio features: MFCCs, Mel-scale spectrograms, and chromagrams. We also determine if utilizing means is more effective in representing the speech signal, given the large number of coefficients produced during the feature extraction process. Finally, we evaluate whether these feature representation techniques are sensitive to speaker information. Our results show that a recurrent neural network architecture in conjunction with all three feature sets yields the best results for the task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arroniz-kubler-2023-question">
<titleInfo>
<title>Was That a Question? Automatic Classification of Discourse Meaning in Spanish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Arróniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Kübler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper examines the effectiveness of different feature representations of audio data in accurately classifying discourse meaning in Spanish. The task involves determining whether an utterance is a declarative sentence, an interrogative, an imperative, etc. We explore how pitch contour can be represented for a discourse-meaning classification task, employing three different audio features: MFCCs, Mel-scale spectrograms, and chromagrams. We also determine if utilizing means is more effective in representing the speech signal, given the large number of coefficients produced during the feature extraction process. Finally, we evaluate whether these feature representation techniques are sensitive to speaker information. Our results show that a recurrent neural network architecture in conjunction with all three feature sets yields the best results for the task.</abstract>
<identifier type="citekey">arroniz-kubler-2023-question</identifier>
<location>
<url>https://aclanthology.org/2023.ranlp-1.15</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>132</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Was That a Question? Automatic Classification of Discourse Meaning in Spanish
%A Arróniz, Santiago
%A Kübler, Sandra
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F arroniz-kubler-2023-question
%X This paper examines the effectiveness of different feature representations of audio data in accurately classifying discourse meaning in Spanish. The task involves determining whether an utterance is a declarative sentence, an interrogative, an imperative, etc. We explore how pitch contour can be represented for a discourse-meaning classification task, employing three different audio features: MFCCs, Mel-scale spectrograms, and chromagrams. We also determine if utilizing means is more effective in representing the speech signal, given the large number of coefficients produced during the feature extraction process. Finally, we evaluate whether these feature representation techniques are sensitive to speaker information. Our results show that a recurrent neural network architecture in conjunction with all three feature sets yields the best results for the task.
%U https://aclanthology.org/2023.ranlp-1.15
%P 132-142
Markdown (Informal)
[Was That a Question? Automatic Classification of Discourse Meaning in Spanish](https://aclanthology.org/2023.ranlp-1.15) (Arróniz & Kübler, RANLP 2023)
ACL