@inproceedings{cui-etal-2025-recent,
title = "Recent Advances in Speech Language Models: A Survey",
author = "Cui, Wenqian and
Yu, Dianzhi and
Jiao, Xiaoqi and
Meng, Ziqiao and
Zhang, Guangyan and
Wang, Qichao and
Guo, Steven Y. and
King, Irwin",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.682/",
doi = "10.18653/v1/2025.acl-long.682",
pages = "13943--13970",
ISBN = "979-8-89176-251-0",
abstract = "Text-based Large Language Models (LLMs) have recently gained significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, highlighting the need for voice-based models. In this context, Speech Language Models (SpeechLMs){---}foundation models designed to understand and generate speech{---}emerge as a promising solution for end-to-end speech interaction. This survey offers a comprehensive overview of recent approaches to building SpeechLMs, outlining their core architectural components, training methodologies, evaluation strategies, and the challenges and potential directions for future research in this rapidly advancing field. The GitHub repository is available at https://github.com/dreamtheater123/Awesome-SpeechLM-Survey"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cui-etal-2025-recent">
<titleInfo>
<title>Recent Advances in Speech Language Models: A Survey</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenqian</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dianzhi</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqi</namePart>
<namePart type="family">Jiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziqiao</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangyan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qichao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="given">Y</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irwin</namePart>
<namePart type="family">King</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 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</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">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Text-based Large Language Models (LLMs) have recently gained significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, highlighting the need for voice-based models. In this context, Speech Language Models (SpeechLMs)—foundation models designed to understand and generate speech—emerge as a promising solution for end-to-end speech interaction. This survey offers a comprehensive overview of recent approaches to building SpeechLMs, outlining their core architectural components, training methodologies, evaluation strategies, and the challenges and potential directions for future research in this rapidly advancing field. The GitHub repository is available at https://github.com/dreamtheater123/Awesome-SpeechLM-Survey</abstract>
<identifier type="citekey">cui-etal-2025-recent</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.682</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.682/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>13943</start>
<end>13970</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recent Advances in Speech Language Models: A Survey
%A Cui, Wenqian
%A Yu, Dianzhi
%A Jiao, Xiaoqi
%A Meng, Ziqiao
%A Zhang, Guangyan
%A Wang, Qichao
%A Guo, Steven Y.
%A King, Irwin
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F cui-etal-2025-recent
%X Text-based Large Language Models (LLMs) have recently gained significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, highlighting the need for voice-based models. In this context, Speech Language Models (SpeechLMs)—foundation models designed to understand and generate speech—emerge as a promising solution for end-to-end speech interaction. This survey offers a comprehensive overview of recent approaches to building SpeechLMs, outlining their core architectural components, training methodologies, evaluation strategies, and the challenges and potential directions for future research in this rapidly advancing field. The GitHub repository is available at https://github.com/dreamtheater123/Awesome-SpeechLM-Survey
%R 10.18653/v1/2025.acl-long.682
%U https://aclanthology.org/2025.acl-long.682/
%U https://doi.org/10.18653/v1/2025.acl-long.682
%P 13943-13970
Markdown (Informal)
[Recent Advances in Speech Language Models: A Survey](https://aclanthology.org/2025.acl-long.682/) (Cui et al., ACL 2025)
ACL
- Wenqian Cui, Dianzhi Yu, Xiaoqi Jiao, Ziqiao Meng, Guangyan Zhang, Qichao Wang, Steven Y. Guo, and Irwin King. 2025. Recent Advances in Speech Language Models: A Survey. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13943–13970, Vienna, Austria. Association for Computational Linguistics.