@inproceedings{chung-etal-2021-chinese,
title = "{C}hinese Medical Speech Recognition with Punctuated Hypothesis",
author = "Chung, Sheng-Luen and
Fan, Jin-Huan and
Ting, Hsien-Wei",
editor = "Lee, Lung-Hao and
Chang, Chia-Hui and
Chen, Kuan-Yu",
booktitle = "Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)",
month = oct,
year = "2021",
address = "Taoyuan, Taiwan",
publisher = "The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)",
url = "https://aclanthology.org/2021.rocling-1.9",
pages = "63--71",
abstract = "Automatic Speech Recognition (ASR) technology presents the possibility for medical professionals to document patient record, diagnosis, postoperative care, patrol records, and etc. that are now done manually. However, earlier research aimed on Chinese medical speech corpus (ChiMeS) has two shortcomings: first is the lack of punctuation, resulting in reduced readability of the output transcript, and second is the poor recognition error rate, affecting its application put to the fields. Accordingly, the contributions of this paper consist of: (1) A punctuated Chinese medical corpus psChiMeS-14 newly annotated from ChiMeS-14, which is the collection of 516 anonymized medical record readouts of 867 minutes long, recorded by 15 professional nursing staff from Taipei Hospital of the Ministry of Health and Welfare. psChiMeS-14 is manually punctuated with: colons, commas, and periods, ready for general end-to-end ASR models. (2) A self-attention based speech recognition solution by conformer networks. Trained by and tested on psChiMeS-14 corpus, the solutions deliver state-of-the-art recognition performance: CER (character error rate) 10.5{\%}, and KER (Keyword error rate) of 13.10{\%}, respectively, which is contrasted to the 15.70{\%} CER and the 22.50{\%} KER by an earlier reported Joint CTC/Attention architecture.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chung-etal-2021-chinese">
<titleInfo>
<title>Chinese Medical Speech Recognition with Punctuated Hypothesis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sheng-Luen</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin-Huan</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsien-Wei</namePart>
<namePart type="family">Ting</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lung-Hao</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuan-Yu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)</publisher>
<place>
<placeTerm type="text">Taoyuan, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic Speech Recognition (ASR) technology presents the possibility for medical professionals to document patient record, diagnosis, postoperative care, patrol records, and etc. that are now done manually. However, earlier research aimed on Chinese medical speech corpus (ChiMeS) has two shortcomings: first is the lack of punctuation, resulting in reduced readability of the output transcript, and second is the poor recognition error rate, affecting its application put to the fields. Accordingly, the contributions of this paper consist of: (1) A punctuated Chinese medical corpus psChiMeS-14 newly annotated from ChiMeS-14, which is the collection of 516 anonymized medical record readouts of 867 minutes long, recorded by 15 professional nursing staff from Taipei Hospital of the Ministry of Health and Welfare. psChiMeS-14 is manually punctuated with: colons, commas, and periods, ready for general end-to-end ASR models. (2) A self-attention based speech recognition solution by conformer networks. Trained by and tested on psChiMeS-14 corpus, the solutions deliver state-of-the-art recognition performance: CER (character error rate) 10.5%, and KER (Keyword error rate) of 13.10%, respectively, which is contrasted to the 15.70% CER and the 22.50% KER by an earlier reported Joint CTC/Attention architecture.</abstract>
<identifier type="citekey">chung-etal-2021-chinese</identifier>
<location>
<url>https://aclanthology.org/2021.rocling-1.9</url>
</location>
<part>
<date>2021-10</date>
<extent unit="page">
<start>63</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chinese Medical Speech Recognition with Punctuated Hypothesis
%A Chung, Sheng-Luen
%A Fan, Jin-Huan
%A Ting, Hsien-Wei
%Y Lee, Lung-Hao
%Y Chang, Chia-Hui
%Y Chen, Kuan-Yu
%S Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)
%D 2021
%8 October
%I The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
%C Taoyuan, Taiwan
%F chung-etal-2021-chinese
%X Automatic Speech Recognition (ASR) technology presents the possibility for medical professionals to document patient record, diagnosis, postoperative care, patrol records, and etc. that are now done manually. However, earlier research aimed on Chinese medical speech corpus (ChiMeS) has two shortcomings: first is the lack of punctuation, resulting in reduced readability of the output transcript, and second is the poor recognition error rate, affecting its application put to the fields. Accordingly, the contributions of this paper consist of: (1) A punctuated Chinese medical corpus psChiMeS-14 newly annotated from ChiMeS-14, which is the collection of 516 anonymized medical record readouts of 867 minutes long, recorded by 15 professional nursing staff from Taipei Hospital of the Ministry of Health and Welfare. psChiMeS-14 is manually punctuated with: colons, commas, and periods, ready for general end-to-end ASR models. (2) A self-attention based speech recognition solution by conformer networks. Trained by and tested on psChiMeS-14 corpus, the solutions deliver state-of-the-art recognition performance: CER (character error rate) 10.5%, and KER (Keyword error rate) of 13.10%, respectively, which is contrasted to the 15.70% CER and the 22.50% KER by an earlier reported Joint CTC/Attention architecture.
%U https://aclanthology.org/2021.rocling-1.9
%P 63-71
Markdown (Informal)
[Chinese Medical Speech Recognition with Punctuated Hypothesis](https://aclanthology.org/2021.rocling-1.9) (Chung et al., ROCLING 2021)
ACL
- Sheng-Luen Chung, Jin-Huan Fan, and Hsien-Wei Ting. 2021. Chinese Medical Speech Recognition with Punctuated Hypothesis. In Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021), pages 63–71, Taoyuan, Taiwan. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP).