@inproceedings{chizzoni-vietti-2024-towards,
title = "Towards an {ASR} System for Documenting Endangered Languages: A Preliminary Study on {S}ardinian",
author = "Chizzoni, Ilaria and
Vietti, Alessandro",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.26/",
pages = "214--220",
ISBN = "979-12-210-7060-6",
abstract = "Speech recognition systems are still highly dependent on textual orthographic resources, posing a challenge for low-resourcelanguages. Recent research leverages self-supervised learning of unlabeled data or employs multilingual models pre-trainedon high resource languages for fine-tuning on the target low-resource language. These are effective approacheswhen the target language has a shared writing tradition, but when we are confronted with mainly spoken languages, beingthem endangered minority languages, dialects, or regional varieties, other than labeled data, we lack a shared metric toassess speech recognition performance. We first provide a research background on ASR for low-resource languages anddescribe the specific linguistic situation of Campidanese Sardinian, we then evaluate five multilingual ASR models usingtraditional evaluation metrics and an exploratory linguistic analysis. The paper addresses key challenges in developing a toolfor researchers to document and analyze the phonetics and phonology of spoken (endangered) languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chizzoni-vietti-2024-towards">
<titleInfo>
<title>Towards an ASR System for Documenting Endangered Languages: A Preliminary Study on Sardinian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ilaria</namePart>
<namePart type="family">Chizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Vietti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</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">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>Speech recognition systems are still highly dependent on textual orthographic resources, posing a challenge for low-resourcelanguages. Recent research leverages self-supervised learning of unlabeled data or employs multilingual models pre-trainedon high resource languages for fine-tuning on the target low-resource language. These are effective approacheswhen the target language has a shared writing tradition, but when we are confronted with mainly spoken languages, beingthem endangered minority languages, dialects, or regional varieties, other than labeled data, we lack a shared metric toassess speech recognition performance. We first provide a research background on ASR for low-resource languages anddescribe the specific linguistic situation of Campidanese Sardinian, we then evaluate five multilingual ASR models usingtraditional evaluation metrics and an exploratory linguistic analysis. The paper addresses key challenges in developing a toolfor researchers to document and analyze the phonetics and phonology of spoken (endangered) languages.</abstract>
<identifier type="citekey">chizzoni-vietti-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.26/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>214</start>
<end>220</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards an ASR System for Documenting Endangered Languages: A Preliminary Study on Sardinian
%A Chizzoni, Ilaria
%A Vietti, Alessandro
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F chizzoni-vietti-2024-towards
%X Speech recognition systems are still highly dependent on textual orthographic resources, posing a challenge for low-resourcelanguages. Recent research leverages self-supervised learning of unlabeled data or employs multilingual models pre-trainedon high resource languages for fine-tuning on the target low-resource language. These are effective approacheswhen the target language has a shared writing tradition, but when we are confronted with mainly spoken languages, beingthem endangered minority languages, dialects, or regional varieties, other than labeled data, we lack a shared metric toassess speech recognition performance. We first provide a research background on ASR for low-resource languages anddescribe the specific linguistic situation of Campidanese Sardinian, we then evaluate five multilingual ASR models usingtraditional evaluation metrics and an exploratory linguistic analysis. The paper addresses key challenges in developing a toolfor researchers to document and analyze the phonetics and phonology of spoken (endangered) languages.
%U https://aclanthology.org/2024.clicit-1.26/
%P 214-220
Markdown (Informal)
[Towards an ASR System for Documenting Endangered Languages: A Preliminary Study on Sardinian](https://aclanthology.org/2024.clicit-1.26/) (Chizzoni & Vietti, CLiC-it 2024)
ACL