@inproceedings{coutinho-etal-2016-assessing,
title = "Assessing the Prosody of Non-Native Speakers of {E}nglish: Measures and Feature Sets",
author = {Coutinho, Eduardo and
H{\"o}nig, Florian and
Zhang, Yue and
Hantke, Simone and
Batliner, Anton and
N{\"o}th, Elmar 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/L16-1211",
pages = "1328--1332",
abstract = "In this paper, we describe a new database with audio recordings of non-native (L2) speakers of English, and the perceptual evaluation experiment conducted with native English speakers for assessing the prosody of each recording. These annotations are then used to compute the gold standard using different methods, and a series of regression experiments is conducted to evaluate their impact on the performance of a regression model predicting the degree of naturalness of L2 speech. Further, we compare the relevance of different feature groups modelling prosody in general (without speech tempo), speech rate and pauses modelling speech tempo (fluency), voice quality, and a variety of spectral features. We also discuss the impact of various fusion strategies on performance. Overall, our results demonstrate that the prosody of non-native speakers of English as L2 can be reliably assessed using supra-segmental audio features; prosodic features seem to be the most important ones.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="coutinho-etal-2016-assessing">
<titleInfo>
<title>Assessing the Prosody of Non-Native Speakers of English: Measures and Feature Sets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eduardo</namePart>
<namePart type="family">Coutinho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Hönig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Anton</namePart>
<namePart type="family">Batliner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elmar</namePart>
<namePart type="family">Nöth</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>In this paper, we describe a new database with audio recordings of non-native (L2) speakers of English, and the perceptual evaluation experiment conducted with native English speakers for assessing the prosody of each recording. These annotations are then used to compute the gold standard using different methods, and a series of regression experiments is conducted to evaluate their impact on the performance of a regression model predicting the degree of naturalness of L2 speech. Further, we compare the relevance of different feature groups modelling prosody in general (without speech tempo), speech rate and pauses modelling speech tempo (fluency), voice quality, and a variety of spectral features. We also discuss the impact of various fusion strategies on performance. Overall, our results demonstrate that the prosody of non-native speakers of English as L2 can be reliably assessed using supra-segmental audio features; prosodic features seem to be the most important ones.</abstract>
<identifier type="citekey">coutinho-etal-2016-assessing</identifier>
<location>
<url>https://aclanthology.org/L16-1211</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1328</start>
<end>1332</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Assessing the Prosody of Non-Native Speakers of English: Measures and Feature Sets
%A Coutinho, Eduardo
%A Hönig, Florian
%A Zhang, Yue
%A Hantke, Simone
%A Batliner, Anton
%A Nöth, Elmar
%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 coutinho-etal-2016-assessing
%X In this paper, we describe a new database with audio recordings of non-native (L2) speakers of English, and the perceptual evaluation experiment conducted with native English speakers for assessing the prosody of each recording. These annotations are then used to compute the gold standard using different methods, and a series of regression experiments is conducted to evaluate their impact on the performance of a regression model predicting the degree of naturalness of L2 speech. Further, we compare the relevance of different feature groups modelling prosody in general (without speech tempo), speech rate and pauses modelling speech tempo (fluency), voice quality, and a variety of spectral features. We also discuss the impact of various fusion strategies on performance. Overall, our results demonstrate that the prosody of non-native speakers of English as L2 can be reliably assessed using supra-segmental audio features; prosodic features seem to be the most important ones.
%U https://aclanthology.org/L16-1211
%P 1328-1332
Markdown (Informal)
[Assessing the Prosody of Non-Native Speakers of English: Measures and Feature Sets](https://aclanthology.org/L16-1211) (Coutinho et al., LREC 2016)
ACL