@inproceedings{coats-2024-coanzse,
title = "{C}o{ANZSE} Audio: Creation of an Online Corpus for Linguistic and Phonetic Analysis of {A}ustralian and {N}ew {Z}ealand Englishes",
author = "Coats, Steven",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.302/",
pages = "3407--3412",
abstract = "CoANZSE Audio is a searchable online version of the Corpus of Australian and New Zealand Spoken English, a 195-million-word collection of geo-located YouTube transcripts of local government channels. In addition to the part-of-speech-tagged and lemmatized transcript data, CoANZSE Audio provides access to almost all of the underlying audio, as well as to forced alignments of the audio with transcript content, in Praat`s TextGrid format. This paper describes the methods used to create the corpus from open-source tools and the architecture of the CoANZSE Audio website. Two possible linguistic analyses based on CoANZSE Audio data are described: use of double modals, a rare syntactic feature, and raising of the mid front vowel /{\varepsilon}/ in New Zealand English. CoANZSE Audio can be considered to be among the first large, free, fully searchable online corpora containing data suitable for acoustic phonetic analyses in addition to lexical, grammatical, and discourse properties of Australian and New Zealand Englishes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="coats-2024-coanzse">
<titleInfo>
<title>CoANZSE Audio: Creation of an Online Corpus for Linguistic and Phonetic Analysis of Australian and New Zealand Englishes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Coats</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</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">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>CoANZSE Audio is a searchable online version of the Corpus of Australian and New Zealand Spoken English, a 195-million-word collection of geo-located YouTube transcripts of local government channels. In addition to the part-of-speech-tagged and lemmatized transcript data, CoANZSE Audio provides access to almost all of the underlying audio, as well as to forced alignments of the audio with transcript content, in Praat‘s TextGrid format. This paper describes the methods used to create the corpus from open-source tools and the architecture of the CoANZSE Audio website. Two possible linguistic analyses based on CoANZSE Audio data are described: use of double modals, a rare syntactic feature, and raising of the mid front vowel /ǎrepsilon/ in New Zealand English. CoANZSE Audio can be considered to be among the first large, free, fully searchable online corpora containing data suitable for acoustic phonetic analyses in addition to lexical, grammatical, and discourse properties of Australian and New Zealand Englishes.</abstract>
<identifier type="citekey">coats-2024-coanzse</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.302/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3407</start>
<end>3412</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoANZSE Audio: Creation of an Online Corpus for Linguistic and Phonetic Analysis of Australian and New Zealand Englishes
%A Coats, Steven
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F coats-2024-coanzse
%X CoANZSE Audio is a searchable online version of the Corpus of Australian and New Zealand Spoken English, a 195-million-word collection of geo-located YouTube transcripts of local government channels. In addition to the part-of-speech-tagged and lemmatized transcript data, CoANZSE Audio provides access to almost all of the underlying audio, as well as to forced alignments of the audio with transcript content, in Praat‘s TextGrid format. This paper describes the methods used to create the corpus from open-source tools and the architecture of the CoANZSE Audio website. Two possible linguistic analyses based on CoANZSE Audio data are described: use of double modals, a rare syntactic feature, and raising of the mid front vowel /ǎrepsilon/ in New Zealand English. CoANZSE Audio can be considered to be among the first large, free, fully searchable online corpora containing data suitable for acoustic phonetic analyses in addition to lexical, grammatical, and discourse properties of Australian and New Zealand Englishes.
%U https://aclanthology.org/2024.lrec-main.302/
%P 3407-3412
Markdown (Informal)
[CoANZSE Audio: Creation of an Online Corpus for Linguistic and Phonetic Analysis of Australian and New Zealand Englishes](https://aclanthology.org/2024.lrec-main.302/) (Coats, LREC-COLING 2024)
ACL