@inproceedings{shen-etal-2026-vocalrep,
title = "{V}ocal{R}ep: Structure-Aware Vocal Representations for Multimodal Generation",
author = "Shen, Da and
Weng, Zhenqiang and
Liu, Tianyu and
Chen, Gongyu and
Shi, Runhua and
Chen, Jiahui and
Ding, Chaofan and
Zhang, Wei-Qiang and
Chen, Zihao",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1785/",
pages = "35850--35865",
ISBN = "979-8-89176-395-1",
abstract = "Modern speech and multimodal generation systems, such as singing voice conversion and audio-driven lip synchronization, critically depend on temporally stable and semantically unambiguous vocal representations. In practical pipelines, such representations are typically derived from music source separation (MSS) applied to mixed musical recordings. However, standard MSS paradigms often aggregate lead vocals and backing harmonies into a single vocal stream. Although multi-stem separation has been explored, existing approaches remain primarily optimized for signal-level reconstruction, often overlooking the intricate structural disentanglement required by downstream generation tasks. From a generation-oriented perspective, this motivates revisiting vocal separation from a representation learning standpoint. To this end, we propose VocalRep, a structure-aware learning framework designed to disentangle lead vocals, harmonies, and accompaniment while enforcing role consistency across long-form audio. By integrating global vocal identity conditioning with ranking-based objectives, VocalRep extracts role-consistent lead vocal representations without relying on explicit pitch or symbolic annotations. Experimental results demonstrate that VocalRep significantly improves performance in downstream singing voice conversion and audio-driven lip synchronization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2026-vocalrep">
<titleInfo>
<title>VocalRep: Structure-Aware Vocal Representations for Multimodal Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Da</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenqiang</namePart>
<namePart type="family">Weng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gongyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Runhua</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahui</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaofan</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Qiang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihao</namePart>
<namePart type="family">Chen</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>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Modern speech and multimodal generation systems, such as singing voice conversion and audio-driven lip synchronization, critically depend on temporally stable and semantically unambiguous vocal representations. In practical pipelines, such representations are typically derived from music source separation (MSS) applied to mixed musical recordings. However, standard MSS paradigms often aggregate lead vocals and backing harmonies into a single vocal stream. Although multi-stem separation has been explored, existing approaches remain primarily optimized for signal-level reconstruction, often overlooking the intricate structural disentanglement required by downstream generation tasks. From a generation-oriented perspective, this motivates revisiting vocal separation from a representation learning standpoint. To this end, we propose VocalRep, a structure-aware learning framework designed to disentangle lead vocals, harmonies, and accompaniment while enforcing role consistency across long-form audio. By integrating global vocal identity conditioning with ranking-based objectives, VocalRep extracts role-consistent lead vocal representations without relying on explicit pitch or symbolic annotations. Experimental results demonstrate that VocalRep significantly improves performance in downstream singing voice conversion and audio-driven lip synchronization.</abstract>
<identifier type="citekey">shen-etal-2026-vocalrep</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1785/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>35850</start>
<end>35865</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VocalRep: Structure-Aware Vocal Representations for Multimodal Generation
%A Shen, Da
%A Weng, Zhenqiang
%A Liu, Tianyu
%A Chen, Gongyu
%A Shi, Runhua
%A Chen, Jiahui
%A Ding, Chaofan
%A Zhang, Wei-Qiang
%A Chen, Zihao
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F shen-etal-2026-vocalrep
%X Modern speech and multimodal generation systems, such as singing voice conversion and audio-driven lip synchronization, critically depend on temporally stable and semantically unambiguous vocal representations. In practical pipelines, such representations are typically derived from music source separation (MSS) applied to mixed musical recordings. However, standard MSS paradigms often aggregate lead vocals and backing harmonies into a single vocal stream. Although multi-stem separation has been explored, existing approaches remain primarily optimized for signal-level reconstruction, often overlooking the intricate structural disentanglement required by downstream generation tasks. From a generation-oriented perspective, this motivates revisiting vocal separation from a representation learning standpoint. To this end, we propose VocalRep, a structure-aware learning framework designed to disentangle lead vocals, harmonies, and accompaniment while enforcing role consistency across long-form audio. By integrating global vocal identity conditioning with ranking-based objectives, VocalRep extracts role-consistent lead vocal representations without relying on explicit pitch or symbolic annotations. Experimental results demonstrate that VocalRep significantly improves performance in downstream singing voice conversion and audio-driven lip synchronization.
%U https://aclanthology.org/2026.findings-acl.1785/
%P 35850-35865
Markdown (Informal)
[VocalRep: Structure-Aware Vocal Representations for Multimodal Generation](https://aclanthology.org/2026.findings-acl.1785/) (Shen et al., Findings 2026)
ACL
- Da Shen, Zhenqiang Weng, Tianyu Liu, Gongyu Chen, Runhua Shi, Jiahui Chen, Chaofan Ding, Wei-Qiang Zhang, and Zihao Chen. 2026. VocalRep: Structure-Aware Vocal Representations for Multimodal Generation. In Findings of the Association for Computational Linguistics: ACL 2026, pages 35850–35865, San Diego, California, United States. Association for Computational Linguistics.