@inproceedings{barker-etal-2022-snuc,
title = "{SN}u{C}: The {S}heffield Numbers Spoken Language Corpus",
author = "Barker, Emma and
Barker, Jon and
Gaizauskas, Robert and
Ma, Ning and
Paramita, Monica Lestari",
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-1.212",
pages = "1978--1984",
abstract = "We present SNuC, the first published corpus of spoken alphanumeric identifiers of the sort typically used as serial and part numbers in the manufacturing sector. The dataset contains recordings and transcriptions of over 50 native British English speakers, speaking over 13,000 multi-character alphanumeric sequences and totalling almost 20 hours of recorded speech. We describe requirements taken into account in the designing the corpus and the methodology used to construct it. We present summary statistics describing the corpus contents, as well as a preliminary investigation into errors in spoken alphanumeric identifiers. We validate the corpus by showing how it can be used to adapt a deep learning neural network based ASR system, resulting in improved recognition accuracy on the task of spoken alphanumeric identifier recognition. Finally, we discuss further potential uses for the corpus and for the tools developed to construct it.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barker-etal-2022-snuc">
<titleInfo>
<title>SNuC: The Sheffield Numbers Spoken Language Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emma</namePart>
<namePart type="family">Barker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="family">Barker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Gaizauskas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ning</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monica</namePart>
<namePart type="given">Lestari</namePart>
<namePart type="family">Paramita</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>We present SNuC, the first published corpus of spoken alphanumeric identifiers of the sort typically used as serial and part numbers in the manufacturing sector. The dataset contains recordings and transcriptions of over 50 native British English speakers, speaking over 13,000 multi-character alphanumeric sequences and totalling almost 20 hours of recorded speech. We describe requirements taken into account in the designing the corpus and the methodology used to construct it. We present summary statistics describing the corpus contents, as well as a preliminary investigation into errors in spoken alphanumeric identifiers. We validate the corpus by showing how it can be used to adapt a deep learning neural network based ASR system, resulting in improved recognition accuracy on the task of spoken alphanumeric identifier recognition. Finally, we discuss further potential uses for the corpus and for the tools developed to construct it.</abstract>
<identifier type="citekey">barker-etal-2022-snuc</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.212</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1978</start>
<end>1984</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SNuC: The Sheffield Numbers Spoken Language Corpus
%A Barker, Emma
%A Barker, Jon
%A Gaizauskas, Robert
%A Ma, Ning
%A Paramita, Monica Lestari
%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 barker-etal-2022-snuc
%X We present SNuC, the first published corpus of spoken alphanumeric identifiers of the sort typically used as serial and part numbers in the manufacturing sector. The dataset contains recordings and transcriptions of over 50 native British English speakers, speaking over 13,000 multi-character alphanumeric sequences and totalling almost 20 hours of recorded speech. We describe requirements taken into account in the designing the corpus and the methodology used to construct it. We present summary statistics describing the corpus contents, as well as a preliminary investigation into errors in spoken alphanumeric identifiers. We validate the corpus by showing how it can be used to adapt a deep learning neural network based ASR system, resulting in improved recognition accuracy on the task of spoken alphanumeric identifier recognition. Finally, we discuss further potential uses for the corpus and for the tools developed to construct it.
%U https://aclanthology.org/2022.lrec-1.212
%P 1978-1984
Markdown (Informal)
[SNuC: The Sheffield Numbers Spoken Language Corpus](https://aclanthology.org/2022.lrec-1.212) (Barker et al., LREC 2022)
ACL
- Emma Barker, Jon Barker, Robert Gaizauskas, Ning Ma, and Monica Lestari Paramita. 2022. SNuC: The Sheffield Numbers Spoken Language Corpus. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1978–1984, Marseille, France. European Language Resources Association.