@inproceedings{wang-etal-2026-dentalvoice,
title = "{D}ental{V}oice: {EMR} Grounded Synthetic Dental Speech Dialogues for {AI} Scribes",
author = "Wang, Zihan and
Zhou, Yi and
Yu, Xuliang and
WU, Hao and
Cai, Qianyi and
Cui, Yi and
Yang, Minghao and
Xiong, Hui",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2248/",
pages = "51132--51156",
ISBN = "979-8-89176-459-0",
abstract = "Dental AI scribes convert chairside dental speech into structured electronic medical records (EMRs). Public data for this task is scarce because dental visits include private speech, regional language, and noisy operatory audio. We introduce DentalVoice, a Chinese dental dialogue and speech dataset for AI scribe research. It contains 13,861 multi-turn dialogues, 162,612 turns, and approximately 274 hours of generated speech. Each case is grounded in a real dental EMR, guided by a dental knowledge graph, conditioned on patient profiles, and augmented with chairside acoustic conditions. We validate the generated dialogues using LLM judges and clinical experts, finding that clinical knowledge retrieval improves safety and professionalism, while persona constraints enhance interaction realism. Next, we benchmark dental automatic speech recognition (ASR) and Subjective-Objective-Assessment-Plan (SOAP) note extraction. Results reveal persistent errors in dialectal ASR, dental terminology recognition, treatment normalization, and distinguishing planned from completed procedures."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-dentalvoice">
<titleInfo>
<title>DentalVoice: EMR Grounded Synthetic Dental Speech Dialogues for AI Scribes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuliang</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">WU</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianyi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Dental AI scribes convert chairside dental speech into structured electronic medical records (EMRs). Public data for this task is scarce because dental visits include private speech, regional language, and noisy operatory audio. We introduce DentalVoice, a Chinese dental dialogue and speech dataset for AI scribe research. It contains 13,861 multi-turn dialogues, 162,612 turns, and approximately 274 hours of generated speech. Each case is grounded in a real dental EMR, guided by a dental knowledge graph, conditioned on patient profiles, and augmented with chairside acoustic conditions. We validate the generated dialogues using LLM judges and clinical experts, finding that clinical knowledge retrieval improves safety and professionalism, while persona constraints enhance interaction realism. Next, we benchmark dental automatic speech recognition (ASR) and Subjective-Objective-Assessment-Plan (SOAP) note extraction. Results reveal persistent errors in dialectal ASR, dental terminology recognition, treatment normalization, and distinguishing planned from completed procedures.</abstract>
<identifier type="citekey">wang-etal-2026-dentalvoice</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2248/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>51132</start>
<end>51156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DentalVoice: EMR Grounded Synthetic Dental Speech Dialogues for AI Scribes
%A Wang, Zihan
%A Zhou, Yi
%A Yu, Xuliang
%A WU, Hao
%A Cai, Qianyi
%A Cui, Yi
%A Yang, Minghao
%A Xiong, Hui
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F wang-etal-2026-dentalvoice
%X Dental AI scribes convert chairside dental speech into structured electronic medical records (EMRs). Public data for this task is scarce because dental visits include private speech, regional language, and noisy operatory audio. We introduce DentalVoice, a Chinese dental dialogue and speech dataset for AI scribe research. It contains 13,861 multi-turn dialogues, 162,612 turns, and approximately 274 hours of generated speech. Each case is grounded in a real dental EMR, guided by a dental knowledge graph, conditioned on patient profiles, and augmented with chairside acoustic conditions. We validate the generated dialogues using LLM judges and clinical experts, finding that clinical knowledge retrieval improves safety and professionalism, while persona constraints enhance interaction realism. Next, we benchmark dental automatic speech recognition (ASR) and Subjective-Objective-Assessment-Plan (SOAP) note extraction. Results reveal persistent errors in dialectal ASR, dental terminology recognition, treatment normalization, and distinguishing planned from completed procedures.
%U https://aclanthology.org/2026.emnlp-main.2248/
%P 51132-51156
Markdown (Informal)
[DentalVoice: EMR Grounded Synthetic Dental Speech Dialogues for AI Scribes](https://aclanthology.org/2026.emnlp-main.2248/) (Wang et al., EMNLP 2026)
ACL
- Zihan Wang, Yi Zhou, Xuliang Yu, Hao WU, Qianyi Cai, Yi Cui, Minghao Yang, and Hui Xiong. 2026. DentalVoice: EMR Grounded Synthetic Dental Speech Dialogues for AI Scribes. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 51132–51156, Budapest, Hungary. Association for Computational Linguistics.