@inproceedings{hantke-etal-2016-introducing,
title = "Introducing the Weighted Trustability Evaluator for Crowdsourcing Exemplified by Speaker Likability Classification",
author = {Hantke, Simone and
Marchi, Erik and
Schuller, Bj{\"o}rn},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
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/L16-1342",
pages = "2156--2161",
abstract = "Crowdsourcing is an arising collaborative approach applicable among many other applications to the area of language and speech processing. In fact, the use of crowdsourcing was already applied in the field of speech processing with promising results. However, only few studies investigated the use of crowdsourcing in computational paralinguistics. In this contribution, we propose a novel evaluator for crowdsourced-based ratings termed Weighted Trustability Evaluator (WTE) which is computed from the rater-dependent consistency over the test questions. We further investigate the reliability of crowdsourced annotations as compared to the ones obtained with traditional labelling procedures, such as constrained listening experiments in laboratories or in controlled environments. This comparison includes an in-depth analysis of obtainable classification performances. The experiments were conducted on the Speaker Likability Database (SLD) already used in the INTERSPEECH Challenge 2012, and the results lend further weight to the assumption that crowdsourcing can be applied as a reliable annotation source for computational paralinguistics given a sufficient number of raters and suited measurements of their reliability.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hantke-etal-2016-introducing">
<titleInfo>
<title>Introducing the Weighted Trustability Evaluator for Crowdsourcing Exemplified by Speaker Likability Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Hantke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Marchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Björn</namePart>
<namePart type="family">Schuller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</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>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>Crowdsourcing is an arising collaborative approach applicable among many other applications to the area of language and speech processing. In fact, the use of crowdsourcing was already applied in the field of speech processing with promising results. However, only few studies investigated the use of crowdsourcing in computational paralinguistics. In this contribution, we propose a novel evaluator for crowdsourced-based ratings termed Weighted Trustability Evaluator (WTE) which is computed from the rater-dependent consistency over the test questions. We further investigate the reliability of crowdsourced annotations as compared to the ones obtained with traditional labelling procedures, such as constrained listening experiments in laboratories or in controlled environments. This comparison includes an in-depth analysis of obtainable classification performances. The experiments were conducted on the Speaker Likability Database (SLD) already used in the INTERSPEECH Challenge 2012, and the results lend further weight to the assumption that crowdsourcing can be applied as a reliable annotation source for computational paralinguistics given a sufficient number of raters and suited measurements of their reliability.</abstract>
<identifier type="citekey">hantke-etal-2016-introducing</identifier>
<location>
<url>https://aclanthology.org/L16-1342</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2156</start>
<end>2161</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Introducing the Weighted Trustability Evaluator for Crowdsourcing Exemplified by Speaker Likability Classification
%A Hantke, Simone
%A Marchi, Erik
%A Schuller, Björn
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%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 hantke-etal-2016-introducing
%X Crowdsourcing is an arising collaborative approach applicable among many other applications to the area of language and speech processing. In fact, the use of crowdsourcing was already applied in the field of speech processing with promising results. However, only few studies investigated the use of crowdsourcing in computational paralinguistics. In this contribution, we propose a novel evaluator for crowdsourced-based ratings termed Weighted Trustability Evaluator (WTE) which is computed from the rater-dependent consistency over the test questions. We further investigate the reliability of crowdsourced annotations as compared to the ones obtained with traditional labelling procedures, such as constrained listening experiments in laboratories or in controlled environments. This comparison includes an in-depth analysis of obtainable classification performances. The experiments were conducted on the Speaker Likability Database (SLD) already used in the INTERSPEECH Challenge 2012, and the results lend further weight to the assumption that crowdsourcing can be applied as a reliable annotation source for computational paralinguistics given a sufficient number of raters and suited measurements of their reliability.
%U https://aclanthology.org/L16-1342
%P 2156-2161
Markdown (Informal)
[Introducing the Weighted Trustability Evaluator for Crowdsourcing Exemplified by Speaker Likability Classification](https://aclanthology.org/L16-1342) (Hantke et al., LREC 2016)
ACL