@inproceedings{jung-etal-2026-sommelier,
title = "Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models",
author = "Jung, Kyudan and
Kim, Jihwan and
Kim, Soyoon and
Kim, Jeonghoon and
Choo, Jaegul and
Park, Cheonbok",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.18/",
pages = "259--284",
ISBN = "979-8-89176-394-4",
abstract = "As the paradigm of AI shifts from text-based LLMs to Speech Language Models (SLMs), there is a growing demand for full-duplex systems capable of real-time, natural human-computer interaction.However, the development of such models is constrained by the scarcity of high-quality, multi-speaker conversational data, as existing large-scale resources are predominantly single-speaker or limited in volume.Addressing the complex dynamics of natural dialogue, such as overlapping and back-channeling remains a challenge, with standard processing pipelines suffering from diarization errors and ASR hallucinations.To bridge this gap, we present a robust and scalable open-source data processing pipeline designed for full-duplex model.Our code and project page are publicly available at https://anonymous-2001-j.github.io/sommelier.github.io/."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jung-etal-2026-sommelier">
<titleInfo>
<title>Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kyudan</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jihwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soyoon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeonghoon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaegul</namePart>
<namePart type="family">Choo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheonbok</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>As the paradigm of AI shifts from text-based LLMs to Speech Language Models (SLMs), there is a growing demand for full-duplex systems capable of real-time, natural human-computer interaction.However, the development of such models is constrained by the scarcity of high-quality, multi-speaker conversational data, as existing large-scale resources are predominantly single-speaker or limited in volume.Addressing the complex dynamics of natural dialogue, such as overlapping and back-channeling remains a challenge, with standard processing pipelines suffering from diarization errors and ASR hallucinations.To bridge this gap, we present a robust and scalable open-source data processing pipeline designed for full-duplex model.Our code and project page are publicly available at https://anonymous-2001-j.github.io/sommelier.github.io/.</abstract>
<identifier type="citekey">jung-etal-2026-sommelier</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.18/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>259</start>
<end>284</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models
%A Jung, Kyudan
%A Kim, Jihwan
%A Kim, Soyoon
%A Kim, Jeonghoon
%A Choo, Jaegul
%A Park, Cheonbok
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F jung-etal-2026-sommelier
%X As the paradigm of AI shifts from text-based LLMs to Speech Language Models (SLMs), there is a growing demand for full-duplex systems capable of real-time, natural human-computer interaction.However, the development of such models is constrained by the scarcity of high-quality, multi-speaker conversational data, as existing large-scale resources are predominantly single-speaker or limited in volume.Addressing the complex dynamics of natural dialogue, such as overlapping and back-channeling remains a challenge, with standard processing pipelines suffering from diarization errors and ASR hallucinations.To bridge this gap, we present a robust and scalable open-source data processing pipeline designed for full-duplex model.Our code and project page are publicly available at https://anonymous-2001-j.github.io/sommelier.github.io/.
%U https://aclanthology.org/2026.acl-industry.18/
%P 259-284
Markdown (Informal)
[Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models](https://aclanthology.org/2026.acl-industry.18/) (Jung et al., ACL 2026)
ACL