@inproceedings{sanni-etal-2025-afrispeech,
title = "Afrispeech-Dialog: A Benchmark Dataset for Spontaneous {E}nglish Conversations in Healthcare and Beyond",
author = "Sanni, Mardhiyah and
Abdullahi, Tassallah and
Kayande, Devendra Deepak and
Ayodele, Emmanuel and
Etori, Naome A and
Mollel, Michael Samwel and
Yekini, Moshood O. and
Okocha, Chibuzor and
Ismaila, Lukman Enegi and
Omofoye, Folafunmi and
Adewale, Boluwatife A. and
Olatunji, Tobi",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.426/",
doi = "10.18653/v1/2025.naacl-long.426",
pages = "8399--8417",
ISBN = "979-8-89176-189-6",
abstract = "Speech technologies are transforming interactions across various sectors, from healthcare to call centers and robots, yet their performance on African-accented conversations remains underexplored. We introduce Afrispeech-Dialog, a benchmark dataset of 50 simulated medical and non-medical African-accented English conversations, designed to evaluate automatic speech recognition (ASR) and related technologies. We assess state-of-the-art (SOTA) speaker diarization and ASR systems on long-form, accented speech, comparing their performance with native accents and discover a 10{\%}+ performance degradation. Additionally, we explore medical conversation summarization capabilities of large language models (LLMs) to demonstrate the impact of ASR errors on downstream medical summaries, providing insights into the challenges and opportunities for speech technologies in the Global South. Our work highlights the need for more inclusive datasets to advance conversational AI in low-resource settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sanni-etal-2025-afrispeech">
<titleInfo>
<title>Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mardhiyah</namePart>
<namePart type="family">Sanni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tassallah</namePart>
<namePart type="family">Abdullahi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Devendra</namePart>
<namePart type="given">Deepak</namePart>
<namePart type="family">Kayande</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Ayodele</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naome</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Etori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">Samwel</namePart>
<namePart type="family">Mollel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moshood</namePart>
<namePart type="given">O</namePart>
<namePart type="family">Yekini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chibuzor</namePart>
<namePart type="family">Okocha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lukman</namePart>
<namePart type="given">Enegi</namePart>
<namePart type="family">Ismaila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Folafunmi</namePart>
<namePart type="family">Omofoye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boluwatife</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Adewale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tobi</namePart>
<namePart type="family">Olatunji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Speech technologies are transforming interactions across various sectors, from healthcare to call centers and robots, yet their performance on African-accented conversations remains underexplored. We introduce Afrispeech-Dialog, a benchmark dataset of 50 simulated medical and non-medical African-accented English conversations, designed to evaluate automatic speech recognition (ASR) and related technologies. We assess state-of-the-art (SOTA) speaker diarization and ASR systems on long-form, accented speech, comparing their performance with native accents and discover a 10%+ performance degradation. Additionally, we explore medical conversation summarization capabilities of large language models (LLMs) to demonstrate the impact of ASR errors on downstream medical summaries, providing insights into the challenges and opportunities for speech technologies in the Global South. Our work highlights the need for more inclusive datasets to advance conversational AI in low-resource settings.</abstract>
<identifier type="citekey">sanni-etal-2025-afrispeech</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.426</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.426/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>8399</start>
<end>8417</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond
%A Sanni, Mardhiyah
%A Abdullahi, Tassallah
%A Kayande, Devendra Deepak
%A Ayodele, Emmanuel
%A Etori, Naome A.
%A Mollel, Michael Samwel
%A Yekini, Moshood O.
%A Okocha, Chibuzor
%A Ismaila, Lukman Enegi
%A Omofoye, Folafunmi
%A Adewale, Boluwatife A.
%A Olatunji, Tobi
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F sanni-etal-2025-afrispeech
%X Speech technologies are transforming interactions across various sectors, from healthcare to call centers and robots, yet their performance on African-accented conversations remains underexplored. We introduce Afrispeech-Dialog, a benchmark dataset of 50 simulated medical and non-medical African-accented English conversations, designed to evaluate automatic speech recognition (ASR) and related technologies. We assess state-of-the-art (SOTA) speaker diarization and ASR systems on long-form, accented speech, comparing their performance with native accents and discover a 10%+ performance degradation. Additionally, we explore medical conversation summarization capabilities of large language models (LLMs) to demonstrate the impact of ASR errors on downstream medical summaries, providing insights into the challenges and opportunities for speech technologies in the Global South. Our work highlights the need for more inclusive datasets to advance conversational AI in low-resource settings.
%R 10.18653/v1/2025.naacl-long.426
%U https://aclanthology.org/2025.naacl-long.426/
%U https://doi.org/10.18653/v1/2025.naacl-long.426
%P 8399-8417
Markdown (Informal)
[Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond](https://aclanthology.org/2025.naacl-long.426/) (Sanni et al., NAACL 2025)
ACL
- Mardhiyah Sanni, Tassallah Abdullahi, Devendra Deepak Kayande, Emmanuel Ayodele, Naome A Etori, Michael Samwel Mollel, Moshood O. Yekini, Chibuzor Okocha, Lukman Enegi Ismaila, Folafunmi Omofoye, Boluwatife A. Adewale, and Tobi Olatunji. 2025. Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 8399–8417, Albuquerque, New Mexico. Association for Computational Linguistics.