@inproceedings{he-etal-2025-meralion,
title = "{MER}a{L}i{ON}-{A}udio{LLM}: Advancing Speech and Language Understanding for {S}ingapore",
author = "He, Yingxu and
Liu, Zhuohan and
Lin, Geyu and
Sun, Shuo and
Wang, Bin and
Zhang, Wenyu and
Zou, Xunlong and
Chen, Nancy F. and
Aw, AiTi",
editor = "Mishra, Pushkar and
Muresan, Smaranda and
Yu, Tao",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-demo.3/",
doi = "10.18653/v1/2025.acl-demo.3",
pages = "22--30",
ISBN = "979-8-89176-253-4",
abstract = "We introduce MERaLiON-AudioLLM, the first general-purpose audio-based large language model designed for multitask learning, with a particular focus on Singlish understanding. Trained on 62 million multimodal instruction samples comprising a total of 260k hours of audio, it exhibits strong generalization across a diverse set of tasks, including{---}but not limited to{---}automatic speech recognition, spoken question answering, speech translation, and paralinguistic analysis. Our results show significant improvements in local speech recognition and task-specific understanding, making MERaLiON-AudioLLM a leading solution for region-specific AI applications. An interactive demo has been developed to enable user-friendly interactions, supported by a backend with customized caching and load-balancing mechanisms. We benchmark the model across a broad range of multilingual and multitask scenarios, where it demonstrates competitive performance compared to other open-source models. The demo page, model weights and videos are publically accessible."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2025-meralion">
<titleInfo>
<title>MERaLiON-AudioLLM: Advancing Speech and Language Understanding for Singapore</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yingxu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuohan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geyu</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xunlong</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AiTi</namePart>
<namePart type="family">Aw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pushkar</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-253-4</identifier>
</relatedItem>
<abstract>We introduce MERaLiON-AudioLLM, the first general-purpose audio-based large language model designed for multitask learning, with a particular focus on Singlish understanding. Trained on 62 million multimodal instruction samples comprising a total of 260k hours of audio, it exhibits strong generalization across a diverse set of tasks, including—but not limited to—automatic speech recognition, spoken question answering, speech translation, and paralinguistic analysis. Our results show significant improvements in local speech recognition and task-specific understanding, making MERaLiON-AudioLLM a leading solution for region-specific AI applications. An interactive demo has been developed to enable user-friendly interactions, supported by a backend with customized caching and load-balancing mechanisms. We benchmark the model across a broad range of multilingual and multitask scenarios, where it demonstrates competitive performance compared to other open-source models. The demo page, model weights and videos are publically accessible.</abstract>
<identifier type="citekey">he-etal-2025-meralion</identifier>
<identifier type="doi">10.18653/v1/2025.acl-demo.3</identifier>
<location>
<url>https://aclanthology.org/2025.acl-demo.3/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>22</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MERaLiON-AudioLLM: Advancing Speech and Language Understanding for Singapore
%A He, Yingxu
%A Liu, Zhuohan
%A Lin, Geyu
%A Sun, Shuo
%A Wang, Bin
%A Zhang, Wenyu
%A Zou, Xunlong
%A Chen, Nancy F.
%A Aw, AiTi
%Y Mishra, Pushkar
%Y Muresan, Smaranda
%Y Yu, Tao
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-253-4
%F he-etal-2025-meralion
%X We introduce MERaLiON-AudioLLM, the first general-purpose audio-based large language model designed for multitask learning, with a particular focus on Singlish understanding. Trained on 62 million multimodal instruction samples comprising a total of 260k hours of audio, it exhibits strong generalization across a diverse set of tasks, including—but not limited to—automatic speech recognition, spoken question answering, speech translation, and paralinguistic analysis. Our results show significant improvements in local speech recognition and task-specific understanding, making MERaLiON-AudioLLM a leading solution for region-specific AI applications. An interactive demo has been developed to enable user-friendly interactions, supported by a backend with customized caching and load-balancing mechanisms. We benchmark the model across a broad range of multilingual and multitask scenarios, where it demonstrates competitive performance compared to other open-source models. The demo page, model weights and videos are publically accessible.
%R 10.18653/v1/2025.acl-demo.3
%U https://aclanthology.org/2025.acl-demo.3/
%U https://doi.org/10.18653/v1/2025.acl-demo.3
%P 22-30
Markdown (Informal)
[MERaLiON-AudioLLM: Advancing Speech and Language Understanding for Singapore](https://aclanthology.org/2025.acl-demo.3/) (He et al., ACL 2025)
ACL
- Yingxu He, Zhuohan Liu, Geyu Lin, Shuo Sun, Bin Wang, Wenyu Zhang, Xunlong Zou, Nancy F. Chen, and AiTi Aw. 2025. MERaLiON-AudioLLM: Advancing Speech and Language Understanding for Singapore. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 22–30, Vienna, Austria. Association for Computational Linguistics.