@inproceedings{jansen-van-vuren-etal-2024-automatic,
title = "Automatic Partitioning of a Code-Switched Speech Corpus Using Mixed-Integer Programming",
author = {Jansen van V{\"u}ren, Joshua Miles and
de Wet, Febe and
Niesler, Thomas},
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.174",
pages = "1944--1952",
abstract = "Defining training, development and test set partitions for speech corpora is usually accomplished by hand. However, for the dataset under investigation, which contains a large number of speakers, eight different languages and code-switching between all the languages, this style of partitioning is not feasible. Therefore, we view the partitioning task as a resource allocation problem and propose to solve it automatically and optimally by the application of mixed-integer linear programming. Using this approach, we are able to partition a new 41.6-hour multilingual corpus of code-switched speech into training, development and testing partitions while maintaining a fixed number of speakers and a specific amount of code-switched speech in the development and test partitions. For this newly partitioned corpus, we present baseline speech recognition results using a state-of-the-art multilingual transformer model (Wav2Vec2-XLS-R) and show that the exclusion of very short utterances ({\textless}1s) results in substantially improved speech recognition performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jansen-van-vuren-etal-2024-automatic">
<titleInfo>
<title>Automatic Partitioning of a Code-Switched Speech Corpus Using Mixed-Integer Programming</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="given">Miles</namePart>
<namePart type="family">Jansen van Vüren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Febe</namePart>
<namePart type="family">de Wet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Niesler</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>Defining training, development and test set partitions for speech corpora is usually accomplished by hand. However, for the dataset under investigation, which contains a large number of speakers, eight different languages and code-switching between all the languages, this style of partitioning is not feasible. Therefore, we view the partitioning task as a resource allocation problem and propose to solve it automatically and optimally by the application of mixed-integer linear programming. Using this approach, we are able to partition a new 41.6-hour multilingual corpus of code-switched speech into training, development and testing partitions while maintaining a fixed number of speakers and a specific amount of code-switched speech in the development and test partitions. For this newly partitioned corpus, we present baseline speech recognition results using a state-of-the-art multilingual transformer model (Wav2Vec2-XLS-R) and show that the exclusion of very short utterances (\textless1s) results in substantially improved speech recognition performance.</abstract>
<identifier type="citekey">jansen-van-vuren-etal-2024-automatic</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.174</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1944</start>
<end>1952</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Partitioning of a Code-Switched Speech Corpus Using Mixed-Integer Programming
%A Jansen van Vüren, Joshua Miles
%A de Wet, Febe
%A Niesler, Thomas
%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 jansen-van-vuren-etal-2024-automatic
%X Defining training, development and test set partitions for speech corpora is usually accomplished by hand. However, for the dataset under investigation, which contains a large number of speakers, eight different languages and code-switching between all the languages, this style of partitioning is not feasible. Therefore, we view the partitioning task as a resource allocation problem and propose to solve it automatically and optimally by the application of mixed-integer linear programming. Using this approach, we are able to partition a new 41.6-hour multilingual corpus of code-switched speech into training, development and testing partitions while maintaining a fixed number of speakers and a specific amount of code-switched speech in the development and test partitions. For this newly partitioned corpus, we present baseline speech recognition results using a state-of-the-art multilingual transformer model (Wav2Vec2-XLS-R) and show that the exclusion of very short utterances (\textless1s) results in substantially improved speech recognition performance.
%U https://aclanthology.org/2024.lrec-main.174
%P 1944-1952
Markdown (Informal)
[Automatic Partitioning of a Code-Switched Speech Corpus Using Mixed-Integer Programming](https://aclanthology.org/2024.lrec-main.174) (Jansen van Vüren et al., LREC-COLING 2024)
ACL