@inproceedings{htun-etal-2024-mymedicon,
title = "my{M}edi{C}on: End-to-End {B}urmese Automatic Speech Recognition for Medical Conversations",
author = "Htun, Hay Man and
Kyaw Thu, Ye and
Chanlekha, Hutchatai and
Funakoshi, Kotaro and
Supnithi, Thepchai",
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.1051",
pages = "12032--12039",
abstract = "End-to-End Automatic Speech Recognition (ASR) models have significantly advanced the field of speech processing by streamlining traditionally complex ASR system pipelines, promising enhanced accuracy and efficiency. Despite these advancements, there is a notable absence of freely available medical conversation speech corpora for Burmese, which is one of the low-resource languages. Addressing this gap, we present a manually curated Burmese Medical Speech Conversations (myMediCon) corpus, encapsulating conversations among medical doctors, nurses, and patients. Utilizing the ESPnet speech processing toolkit, we explore End-to-End ASR models for the Burmese language, focus on Transformer and Recurrent Neural Network (RNN) architectures. Our corpus comprises 12 speakers, including three males and nine females, with a total speech duration of nearly 11 hours within the medical domain. To assess the ASR performance, we applied word and syllable segmentation to the text corpus. ASR models were evaluated using Character Error Rate (CER), Word Error Rate (WER), and Translation Error Rate (TER). The experimental results indicate that the RNN-based Burmese speech recognition with syllable-level segmentation achieved the best performance, yielding a CER of 9.7{\%}. Moreover, the RNN approach significantly outperformed the Transformer model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="htun-etal-2024-mymedicon">
<titleInfo>
<title>myMediCon: End-to-End Burmese Automatic Speech Recognition for Medical Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hay</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Htun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="family">Kyaw Thu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hutchatai</namePart>
<namePart type="family">Chanlekha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kotaro</namePart>
<namePart type="family">Funakoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thepchai</namePart>
<namePart type="family">Supnithi</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>End-to-End Automatic Speech Recognition (ASR) models have significantly advanced the field of speech processing by streamlining traditionally complex ASR system pipelines, promising enhanced accuracy and efficiency. Despite these advancements, there is a notable absence of freely available medical conversation speech corpora for Burmese, which is one of the low-resource languages. Addressing this gap, we present a manually curated Burmese Medical Speech Conversations (myMediCon) corpus, encapsulating conversations among medical doctors, nurses, and patients. Utilizing the ESPnet speech processing toolkit, we explore End-to-End ASR models for the Burmese language, focus on Transformer and Recurrent Neural Network (RNN) architectures. Our corpus comprises 12 speakers, including three males and nine females, with a total speech duration of nearly 11 hours within the medical domain. To assess the ASR performance, we applied word and syllable segmentation to the text corpus. ASR models were evaluated using Character Error Rate (CER), Word Error Rate (WER), and Translation Error Rate (TER). The experimental results indicate that the RNN-based Burmese speech recognition with syllable-level segmentation achieved the best performance, yielding a CER of 9.7%. Moreover, the RNN approach significantly outperformed the Transformer model.</abstract>
<identifier type="citekey">htun-etal-2024-mymedicon</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1051</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12032</start>
<end>12039</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T myMediCon: End-to-End Burmese Automatic Speech Recognition for Medical Conversations
%A Htun, Hay Man
%A Kyaw Thu, Ye
%A Chanlekha, Hutchatai
%A Funakoshi, Kotaro
%A Supnithi, Thepchai
%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 htun-etal-2024-mymedicon
%X End-to-End Automatic Speech Recognition (ASR) models have significantly advanced the field of speech processing by streamlining traditionally complex ASR system pipelines, promising enhanced accuracy and efficiency. Despite these advancements, there is a notable absence of freely available medical conversation speech corpora for Burmese, which is one of the low-resource languages. Addressing this gap, we present a manually curated Burmese Medical Speech Conversations (myMediCon) corpus, encapsulating conversations among medical doctors, nurses, and patients. Utilizing the ESPnet speech processing toolkit, we explore End-to-End ASR models for the Burmese language, focus on Transformer and Recurrent Neural Network (RNN) architectures. Our corpus comprises 12 speakers, including three males and nine females, with a total speech duration of nearly 11 hours within the medical domain. To assess the ASR performance, we applied word and syllable segmentation to the text corpus. ASR models were evaluated using Character Error Rate (CER), Word Error Rate (WER), and Translation Error Rate (TER). The experimental results indicate that the RNN-based Burmese speech recognition with syllable-level segmentation achieved the best performance, yielding a CER of 9.7%. Moreover, the RNN approach significantly outperformed the Transformer model.
%U https://aclanthology.org/2024.lrec-main.1051
%P 12032-12039
Markdown (Informal)
[myMediCon: End-to-End Burmese Automatic Speech Recognition for Medical Conversations](https://aclanthology.org/2024.lrec-main.1051) (Htun et al., LREC-COLING 2024)
ACL