@inproceedings{van-dijk-etal-2025-box,
title = "Out of the Box, into the Clinic? Evaluating State-of-the-Art {ASR} for Clinical Applications for Older Adults",
author = "Van Dijk, Bram and
Kuiper, Tiberon and
Aoulad si Ahmed, Sirin and
Lefebvre, Armel and
Johnson, Jake and
Duin, Jan and
Mooijaart, Simon and
Spruit, Marco",
editor = "Blodgett, Su Lin and
Curry, Amanda Cercas and
Dev, Sunipa and
Li, Siyan and
Madaio, Michael and
Wang, Jack and
Wu, Sherry Tongshuang and
Xiao, Ziang and
Yang, Diyi",
booktitle = "Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.hcinlp-1.7/",
pages = "72--78",
ISBN = "979-8-89176-353-1",
abstract = "Voice-controlled interfaces can support older adults in clinical contexts {--} with chatbots being a prime example {--} but reliable Automatic Speech Recognition (ASR) for underrepresented groups remains a bottleneck. This study evaluates state-of-the-art ASR models on language use of older Dutch adults, who interacted with the Welzijn.AI chatbot designed for geriatric contexts. We benchmark generic multilingual ASR models, and models fine-tuned for Dutch spoken by older adults, while also considering processing speed. Our results show that generic multilingual models outperform fine-tuned models, which suggests recent ASR models can generalise well out of the box to real-world datasets. Moreover, our results indicate that truncating generic models is helpful in balancing the accuracy-speed trade-off. Nonetheless, we also find inputs which cause a high word error rate and place them in context."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-dijk-etal-2025-box">
<titleInfo>
<title>Out of the Box, into the Clinic? Evaluating State-of-the-Art ASR for Clinical Applications for Older Adults</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bram</namePart>
<namePart type="family">Van Dijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiberon</namePart>
<namePart type="family">Kuiper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirin</namePart>
<namePart type="family">Aoulad si Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Armel</namePart>
<namePart type="family">Lefebvre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jake</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Duin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mooijaart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Spruit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Su</namePart>
<namePart type="given">Lin</namePart>
<namePart type="family">Blodgett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="given">Cercas</namePart>
<namePart type="family">Curry</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">Siyan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Madaio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sherry</namePart>
<namePart type="given">Tongshuang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziang</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-353-1</identifier>
</relatedItem>
<abstract>Voice-controlled interfaces can support older adults in clinical contexts – with chatbots being a prime example – but reliable Automatic Speech Recognition (ASR) for underrepresented groups remains a bottleneck. This study evaluates state-of-the-art ASR models on language use of older Dutch adults, who interacted with the Welzijn.AI chatbot designed for geriatric contexts. We benchmark generic multilingual ASR models, and models fine-tuned for Dutch spoken by older adults, while also considering processing speed. Our results show that generic multilingual models outperform fine-tuned models, which suggests recent ASR models can generalise well out of the box to real-world datasets. Moreover, our results indicate that truncating generic models is helpful in balancing the accuracy-speed trade-off. Nonetheless, we also find inputs which cause a high word error rate and place them in context.</abstract>
<identifier type="citekey">van-dijk-etal-2025-box</identifier>
<location>
<url>https://aclanthology.org/2025.hcinlp-1.7/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>72</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Out of the Box, into the Clinic? Evaluating State-of-the-Art ASR for Clinical Applications for Older Adults
%A Van Dijk, Bram
%A Kuiper, Tiberon
%A Aoulad si Ahmed, Sirin
%A Lefebvre, Armel
%A Johnson, Jake
%A Duin, Jan
%A Mooijaart, Simon
%A Spruit, Marco
%Y Blodgett, Su Lin
%Y Curry, Amanda Cercas
%Y Dev, Sunipa
%Y Li, Siyan
%Y Madaio, Michael
%Y Wang, Jack
%Y Wu, Sherry Tongshuang
%Y Xiao, Ziang
%Y Yang, Diyi
%S Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-353-1
%F van-dijk-etal-2025-box
%X Voice-controlled interfaces can support older adults in clinical contexts – with chatbots being a prime example – but reliable Automatic Speech Recognition (ASR) for underrepresented groups remains a bottleneck. This study evaluates state-of-the-art ASR models on language use of older Dutch adults, who interacted with the Welzijn.AI chatbot designed for geriatric contexts. We benchmark generic multilingual ASR models, and models fine-tuned for Dutch spoken by older adults, while also considering processing speed. Our results show that generic multilingual models outperform fine-tuned models, which suggests recent ASR models can generalise well out of the box to real-world datasets. Moreover, our results indicate that truncating generic models is helpful in balancing the accuracy-speed trade-off. Nonetheless, we also find inputs which cause a high word error rate and place them in context.
%U https://aclanthology.org/2025.hcinlp-1.7/
%P 72-78
Markdown (Informal)
[Out of the Box, into the Clinic? Evaluating State-of-the-Art ASR for Clinical Applications for Older Adults](https://aclanthology.org/2025.hcinlp-1.7/) (Van Dijk et al., HCINLP 2025)
ACL
- Bram Van Dijk, Tiberon Kuiper, Sirin Aoulad si Ahmed, Armel Lefebvre, Jake Johnson, Jan Duin, Simon Mooijaart, and Marco Spruit. 2025. Out of the Box, into the Clinic? Evaluating State-of-the-Art ASR for Clinical Applications for Older Adults. In Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP), pages 72–78, Suzhou, China. Association for Computational Linguistics.