@inproceedings{le-duc-2024-vietmed-dataset,
title = "{V}iet{M}ed: A Dataset and Benchmark for Automatic Speech Recognition of {V}ietnamese in the Medical Domain",
author = "Le-Duc, Khai",
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.1509",
pages = "17365--17370",
abstract = "Due to privacy restrictions, there{'}s a shortage of publicly available speech recognition datasets in the medical domain. In this work, we present VietMed - a Vietnamese speech recognition dataset in the medical domain comprising 16h of labeled medical speech, 1000h of unlabeled medical speech and 1200h of unlabeled general-domain speech. To our best knowledge, VietMed is by far the world{'}s largest public medical speech recognition dataset in 7 aspects: total duration, number of speakers, diseases, recording conditions, speaker roles, unique medical terms and accents. VietMed is also by far the largest public Vietnamese speech dataset in terms of total duration. Additionally, we are the first to present a medical ASR dataset covering all ICD-10 disease groups and all accents within a country. Moreover, we release the first public large-scale pre-trained models for Vietnamese ASR, w2v2-Viet and XLSR-53-Viet, along with the first public large-scale fine-tuned models for medical ASR. Even without any medical data in unsupervised pre-training, our best pre-trained model XLSR-53-Viet generalizes very well to the medical domain by outperforming state-of-the-art XLSR-53, from 51.8{\%} to 29.6{\%} WER on test set (a relative reduction of more than 40{\%}). All code, data and models are made publicly available here.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-duc-2024-vietmed-dataset">
<titleInfo>
<title>VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khai</namePart>
<namePart type="family">Le-Duc</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>Due to privacy restrictions, there’s a shortage of publicly available speech recognition datasets in the medical domain. In this work, we present VietMed - a Vietnamese speech recognition dataset in the medical domain comprising 16h of labeled medical speech, 1000h of unlabeled medical speech and 1200h of unlabeled general-domain speech. To our best knowledge, VietMed is by far the world’s largest public medical speech recognition dataset in 7 aspects: total duration, number of speakers, diseases, recording conditions, speaker roles, unique medical terms and accents. VietMed is also by far the largest public Vietnamese speech dataset in terms of total duration. Additionally, we are the first to present a medical ASR dataset covering all ICD-10 disease groups and all accents within a country. Moreover, we release the first public large-scale pre-trained models for Vietnamese ASR, w2v2-Viet and XLSR-53-Viet, along with the first public large-scale fine-tuned models for medical ASR. Even without any medical data in unsupervised pre-training, our best pre-trained model XLSR-53-Viet generalizes very well to the medical domain by outperforming state-of-the-art XLSR-53, from 51.8% to 29.6% WER on test set (a relative reduction of more than 40%). All code, data and models are made publicly available here.</abstract>
<identifier type="citekey">le-duc-2024-vietmed-dataset</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1509</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>17365</start>
<end>17370</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain
%A Le-Duc, Khai
%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 le-duc-2024-vietmed-dataset
%X Due to privacy restrictions, there’s a shortage of publicly available speech recognition datasets in the medical domain. In this work, we present VietMed - a Vietnamese speech recognition dataset in the medical domain comprising 16h of labeled medical speech, 1000h of unlabeled medical speech and 1200h of unlabeled general-domain speech. To our best knowledge, VietMed is by far the world’s largest public medical speech recognition dataset in 7 aspects: total duration, number of speakers, diseases, recording conditions, speaker roles, unique medical terms and accents. VietMed is also by far the largest public Vietnamese speech dataset in terms of total duration. Additionally, we are the first to present a medical ASR dataset covering all ICD-10 disease groups and all accents within a country. Moreover, we release the first public large-scale pre-trained models for Vietnamese ASR, w2v2-Viet and XLSR-53-Viet, along with the first public large-scale fine-tuned models for medical ASR. Even without any medical data in unsupervised pre-training, our best pre-trained model XLSR-53-Viet generalizes very well to the medical domain by outperforming state-of-the-art XLSR-53, from 51.8% to 29.6% WER on test set (a relative reduction of more than 40%). All code, data and models are made publicly available here.
%U https://aclanthology.org/2024.lrec-main.1509
%P 17365-17370
Markdown (Informal)
[VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain](https://aclanthology.org/2024.lrec-main.1509) (Le-Duc, LREC-COLING 2024)
ACL