@inproceedings{zhao-chodroff-2022-mandi,
title = "The {M}an{D}i Corpus: A Spoken Corpus of {M}andarin Regional Dialects",
author = "Zhao, Liang and
Chodroff, Eleanor",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.213",
pages = "1985--1990",
abstract = "In the present paper, we introduce the ManDi Corpus, a spoken corpus of regional Mandarin dialects and Standard Mandarin. The corpus currently contains 357 recordings (about 9.6 hours) of monosyllabic words, disyllabic words, short sentences, a short passage and a poem, each produced in Standard Mandarin and in one of six regional Mandarin dialects: Beijing, Chengdu, Jinan, Taiyuan, Wuhan, and Xi{'}an Mandarin from 36 speakers. The corpus was collected remotely using participant-controlled smartphone recording apps. Word- and phone-level alignments were generated using Praat and the Montreal Forced Aligner. The pilot study of dialect-specific tone systems showed that with practicable design and decent recording quality, remotely collected speech data can be suitable for analysis of relative patterns in acoustic-phonetic realization. The corpus is available on OSF (\url{https://osf.io/fgv4w/}) for non-commercial use under a CC BY-NC 3.0 license.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-chodroff-2022-mandi">
<titleInfo>
<title>The ManDi Corpus: A Spoken Corpus of Mandarin Regional Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eleanor</namePart>
<namePart type="family">Chodroff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the present paper, we introduce the ManDi Corpus, a spoken corpus of regional Mandarin dialects and Standard Mandarin. The corpus currently contains 357 recordings (about 9.6 hours) of monosyllabic words, disyllabic words, short sentences, a short passage and a poem, each produced in Standard Mandarin and in one of six regional Mandarin dialects: Beijing, Chengdu, Jinan, Taiyuan, Wuhan, and Xi’an Mandarin from 36 speakers. The corpus was collected remotely using participant-controlled smartphone recording apps. Word- and phone-level alignments were generated using Praat and the Montreal Forced Aligner. The pilot study of dialect-specific tone systems showed that with practicable design and decent recording quality, remotely collected speech data can be suitable for analysis of relative patterns in acoustic-phonetic realization. The corpus is available on OSF (https://osf.io/fgv4w/) for non-commercial use under a CC BY-NC 3.0 license.</abstract>
<identifier type="citekey">zhao-chodroff-2022-mandi</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.213</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1985</start>
<end>1990</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The ManDi Corpus: A Spoken Corpus of Mandarin Regional Dialects
%A Zhao, Liang
%A Chodroff, Eleanor
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F zhao-chodroff-2022-mandi
%X In the present paper, we introduce the ManDi Corpus, a spoken corpus of regional Mandarin dialects and Standard Mandarin. The corpus currently contains 357 recordings (about 9.6 hours) of monosyllabic words, disyllabic words, short sentences, a short passage and a poem, each produced in Standard Mandarin and in one of six regional Mandarin dialects: Beijing, Chengdu, Jinan, Taiyuan, Wuhan, and Xi’an Mandarin from 36 speakers. The corpus was collected remotely using participant-controlled smartphone recording apps. Word- and phone-level alignments were generated using Praat and the Montreal Forced Aligner. The pilot study of dialect-specific tone systems showed that with practicable design and decent recording quality, remotely collected speech data can be suitable for analysis of relative patterns in acoustic-phonetic realization. The corpus is available on OSF (https://osf.io/fgv4w/) for non-commercial use under a CC BY-NC 3.0 license.
%U https://aclanthology.org/2022.lrec-1.213
%P 1985-1990
Markdown (Informal)
[The ManDi Corpus: A Spoken Corpus of Mandarin Regional Dialects](https://aclanthology.org/2022.lrec-1.213) (Zhao & Chodroff, LREC 2022)
ACL