@inproceedings{gulli-etal-2024-fine-tuning,
title = "Fine-Tuning a Pre-Trained {W}av2{V}ec2 Model for Automatic Speech Recognition- Experiments with De Zahrar Sproche",
author = "Gulli, Andrea and
Costantini, Francesco and
Sidraschi, Diego and
Li Destri, Emanuela",
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.645",
pages = "7336--7342",
abstract = "We present the results of an Automatic Speech Recognition system developed to support linguistic documentation efforts. The test case is the zahrar sproche language, a Southern Bavarian variety spoken in the language island of Sauris/Zahre in Italy. We collected a dataset of 9,000 words and approximately 80 minutes of speech. The goal is to reduce the transcription workload of field linguists. The method used is a deep learning approach based on the language-specific tuning of a generic pre-trained representation model, XLS-R. The transcription quality of the experiments on the collected dataset is promising. We test the model{'}s performance on some fieldwork historical recordings, report the results, and evaluate them qualitatively. Finally, we indicate possibilities for improvement in this challenging task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gulli-etal-2024-fine-tuning">
<titleInfo>
<title>Fine-Tuning a Pre-Trained Wav2Vec2 Model for Automatic Speech Recognition- Experiments with De Zahrar Sproche</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Gulli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Costantini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Sidraschi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emanuela</namePart>
<namePart type="family">Li Destri</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>We present the results of an Automatic Speech Recognition system developed to support linguistic documentation efforts. The test case is the zahrar sproche language, a Southern Bavarian variety spoken in the language island of Sauris/Zahre in Italy. We collected a dataset of 9,000 words and approximately 80 minutes of speech. The goal is to reduce the transcription workload of field linguists. The method used is a deep learning approach based on the language-specific tuning of a generic pre-trained representation model, XLS-R. The transcription quality of the experiments on the collected dataset is promising. We test the model’s performance on some fieldwork historical recordings, report the results, and evaluate them qualitatively. Finally, we indicate possibilities for improvement in this challenging task.</abstract>
<identifier type="citekey">gulli-etal-2024-fine-tuning</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.645</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7336</start>
<end>7342</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-Tuning a Pre-Trained Wav2Vec2 Model for Automatic Speech Recognition- Experiments with De Zahrar Sproche
%A Gulli, Andrea
%A Costantini, Francesco
%A Sidraschi, Diego
%A Li Destri, Emanuela
%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 gulli-etal-2024-fine-tuning
%X We present the results of an Automatic Speech Recognition system developed to support linguistic documentation efforts. The test case is the zahrar sproche language, a Southern Bavarian variety spoken in the language island of Sauris/Zahre in Italy. We collected a dataset of 9,000 words and approximately 80 minutes of speech. The goal is to reduce the transcription workload of field linguists. The method used is a deep learning approach based on the language-specific tuning of a generic pre-trained representation model, XLS-R. The transcription quality of the experiments on the collected dataset is promising. We test the model’s performance on some fieldwork historical recordings, report the results, and evaluate them qualitatively. Finally, we indicate possibilities for improvement in this challenging task.
%U https://aclanthology.org/2024.lrec-main.645
%P 7336-7342
Markdown (Informal)
[Fine-Tuning a Pre-Trained Wav2Vec2 Model for Automatic Speech Recognition- Experiments with De Zahrar Sproche](https://aclanthology.org/2024.lrec-main.645) (Gulli et al., LREC-COLING 2024)
ACL