@inproceedings{alrashoudi-etal-2024-arabic,
title = "{A}rabic Speech Recognition of zero-resourced Languages: A case of {S}hehri (Jibbali) Language",
author = "Alrashoudi, Norah A. and
Alshahri, Omar Said and
Al-Khalifa, Hend",
editor = "Al-Khalifa, Hend and
Darwish, Kareem and
Mubarak, Hamdy and
Ali, Mona and
Elsayed, Tamer",
booktitle = "Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.osact-1.10",
pages = "84--92",
abstract = "Many under-resourced languages lack computational resources for automatic speech recognition (ASR) due to data scarcity issues. This makes developing accurate ASR models challenging. Shehri or Jibbali, spoken in Oman, lacks extensive annotated speech data. This paper aims to improve an ASR model for this under-resourced language. We collected a Shehri (Jibbali) speech corpus and utilized transfer learning by fine-tuning pre-trained ASR models on this dataset. Specifically, models like Wav2Vec2.0, HuBERT and Whisper were fine-tuned using techniques like parameter-efficient fine-tuning. Evaluation using word error rate (WER) and character error rate (CER) showed that the Whisper model, fine-tuned on the Shehri (Jibbali) dataset, significantly outperformed other models, with the best results from Whisper-medium achieving 3.5{\%} WER. This demonstrates the effectiveness of transfer learning for resource-constrained tasks, showing high zero-shot performance of pre-trained models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alrashoudi-etal-2024-arabic">
<titleInfo>
<title>Arabic Speech Recognition of zero-resourced Languages: A case of Shehri (Jibbali) Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Norah</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Alrashoudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="given">Said</namePart>
<namePart type="family">Alshahri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</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 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</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>Many under-resourced languages lack computational resources for automatic speech recognition (ASR) due to data scarcity issues. This makes developing accurate ASR models challenging. Shehri or Jibbali, spoken in Oman, lacks extensive annotated speech data. This paper aims to improve an ASR model for this under-resourced language. We collected a Shehri (Jibbali) speech corpus and utilized transfer learning by fine-tuning pre-trained ASR models on this dataset. Specifically, models like Wav2Vec2.0, HuBERT and Whisper were fine-tuned using techniques like parameter-efficient fine-tuning. Evaluation using word error rate (WER) and character error rate (CER) showed that the Whisper model, fine-tuned on the Shehri (Jibbali) dataset, significantly outperformed other models, with the best results from Whisper-medium achieving 3.5% WER. This demonstrates the effectiveness of transfer learning for resource-constrained tasks, showing high zero-shot performance of pre-trained models.</abstract>
<identifier type="citekey">alrashoudi-etal-2024-arabic</identifier>
<location>
<url>https://aclanthology.org/2024.osact-1.10</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>84</start>
<end>92</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Speech Recognition of zero-resourced Languages: A case of Shehri (Jibbali) Language
%A Alrashoudi, Norah A.
%A Alshahri, Omar Said
%A Al-Khalifa, Hend
%Y Al-Khalifa, Hend
%Y Darwish, Kareem
%Y Mubarak, Hamdy
%Y Ali, Mona
%Y Elsayed, Tamer
%S Proceedings of the 6th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT) with Shared Tasks on Arabic LLMs Hallucination and Dialect to MSA Machine Translation @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F alrashoudi-etal-2024-arabic
%X Many under-resourced languages lack computational resources for automatic speech recognition (ASR) due to data scarcity issues. This makes developing accurate ASR models challenging. Shehri or Jibbali, spoken in Oman, lacks extensive annotated speech data. This paper aims to improve an ASR model for this under-resourced language. We collected a Shehri (Jibbali) speech corpus and utilized transfer learning by fine-tuning pre-trained ASR models on this dataset. Specifically, models like Wav2Vec2.0, HuBERT and Whisper were fine-tuned using techniques like parameter-efficient fine-tuning. Evaluation using word error rate (WER) and character error rate (CER) showed that the Whisper model, fine-tuned on the Shehri (Jibbali) dataset, significantly outperformed other models, with the best results from Whisper-medium achieving 3.5% WER. This demonstrates the effectiveness of transfer learning for resource-constrained tasks, showing high zero-shot performance of pre-trained models.
%U https://aclanthology.org/2024.osact-1.10
%P 84-92
Markdown (Informal)
[Arabic Speech Recognition of zero-resourced Languages: A case of Shehri (Jibbali) Language](https://aclanthology.org/2024.osact-1.10) (Alrashoudi et al., OSACT-WS 2024)
ACL