@inproceedings{tsoukala-etal-2023-asr,
title = "{ASR} pipeline for low-resourced languages: A case study on Pomak",
author = "Tsoukala, Chara and
Kritsis, Kosmas and
Douros, Ioannis and
Katsamanis, Athanasios and
Kokkas, Nikolaos and
Arampatzakis, Vasileios and
Sevetlidis, Vasileios and
Markantonatou, Stella and
Pavlidis, George",
editor = "Serikov, Oleg and
Voloshina, Ekaterina and
Postnikova, Anna and
Klyachko, Elena and
Vylomova, Ekaterina and
Shavrina, Tatiana and
Le Ferrand, Eric and
Malykh, Valentin and
Tyers, Francis and
Arkhangelskiy, Timofey and
Mikhailov, Vladislav",
booktitle = "Proceedings of the Second Workshop on NLP Applications to Field Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.fieldmatters-1.5",
doi = "10.18653/v1/2023.fieldmatters-1.5",
pages = "40--45",
abstract = "Automatic Speech Recognition (ASR) models can aid field linguists by facilitating the creation of text corpora from oral material. Training ASR systems for low-resource languages can be a challenging task not only due to lack of resources but also due to the work required for the preparation of a training dataset. We present a pipeline for data processing and ASR model training for low-resourced languages, based on the language family. As a case study, we collected recordings of Pomak, an endangered South East Slavic language variety spoken in Greece. Using the proposed pipeline, we trained the first Pomak ASR model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tsoukala-etal-2023-asr">
<titleInfo>
<title>ASR pipeline for low-resourced languages: A case study on Pomak</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chara</namePart>
<namePart type="family">Tsoukala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kosmas</namePart>
<namePart type="family">Kritsis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Douros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Athanasios</namePart>
<namePart type="family">Katsamanis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Kokkas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasileios</namePart>
<namePart type="family">Arampatzakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasileios</namePart>
<namePart type="family">Sevetlidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stella</namePart>
<namePart type="family">Markantonatou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Pavlidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on NLP Applications to Field Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Serikov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Voloshina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Postnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Klyachko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Shavrina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Le Ferrand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timofey</namePart>
<namePart type="family">Arkhangelskiy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vladislav</namePart>
<namePart type="family">Mikhailov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic Speech Recognition (ASR) models can aid field linguists by facilitating the creation of text corpora from oral material. Training ASR systems for low-resource languages can be a challenging task not only due to lack of resources but also due to the work required for the preparation of a training dataset. We present a pipeline for data processing and ASR model training for low-resourced languages, based on the language family. As a case study, we collected recordings of Pomak, an endangered South East Slavic language variety spoken in Greece. Using the proposed pipeline, we trained the first Pomak ASR model.</abstract>
<identifier type="citekey">tsoukala-etal-2023-asr</identifier>
<identifier type="doi">10.18653/v1/2023.fieldmatters-1.5</identifier>
<location>
<url>https://aclanthology.org/2023.fieldmatters-1.5</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>40</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ASR pipeline for low-resourced languages: A case study on Pomak
%A Tsoukala, Chara
%A Kritsis, Kosmas
%A Douros, Ioannis
%A Katsamanis, Athanasios
%A Kokkas, Nikolaos
%A Arampatzakis, Vasileios
%A Sevetlidis, Vasileios
%A Markantonatou, Stella
%A Pavlidis, George
%Y Serikov, Oleg
%Y Voloshina, Ekaterina
%Y Postnikova, Anna
%Y Klyachko, Elena
%Y Vylomova, Ekaterina
%Y Shavrina, Tatiana
%Y Le Ferrand, Eric
%Y Malykh, Valentin
%Y Tyers, Francis
%Y Arkhangelskiy, Timofey
%Y Mikhailov, Vladislav
%S Proceedings of the Second Workshop on NLP Applications to Field Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F tsoukala-etal-2023-asr
%X Automatic Speech Recognition (ASR) models can aid field linguists by facilitating the creation of text corpora from oral material. Training ASR systems for low-resource languages can be a challenging task not only due to lack of resources but also due to the work required for the preparation of a training dataset. We present a pipeline for data processing and ASR model training for low-resourced languages, based on the language family. As a case study, we collected recordings of Pomak, an endangered South East Slavic language variety spoken in Greece. Using the proposed pipeline, we trained the first Pomak ASR model.
%R 10.18653/v1/2023.fieldmatters-1.5
%U https://aclanthology.org/2023.fieldmatters-1.5
%U https://doi.org/10.18653/v1/2023.fieldmatters-1.5
%P 40-45
Markdown (Informal)
[ASR pipeline for low-resourced languages: A case study on Pomak](https://aclanthology.org/2023.fieldmatters-1.5) (Tsoukala et al., FieldMatters 2023)
ACL
- Chara Tsoukala, Kosmas Kritsis, Ioannis Douros, Athanasios Katsamanis, Nikolaos Kokkas, Vasileios Arampatzakis, Vasileios Sevetlidis, Stella Markantonatou, and George Pavlidis. 2023. ASR pipeline for low-resourced languages: A case study on Pomak. In Proceedings of the Second Workshop on NLP Applications to Field Linguistics, pages 40–45, Dubrovnik, Croatia. Association for Computational Linguistics.