@inproceedings{prokopiou-etal-2026-labelbuddy,
title = "{L}abel{B}uddy: An Open Source Music and Audio Language Annotation Tagging Tool Using {AI} Assistance",
author = "Prokopiou, Ioannis and
Sina, Ioannis and
Kounelis, Agisilaos and
Vikatos, Pantelis and
Stafylakis, Themos",
editor = "Epure, Elena V. and
Oramas, Sergio and
Doh, SeungHeon and
Ramoneda, Pedro and
Kruspe, Anna and
Sordo, Mohamed",
booktitle = "Proceedings of the 4th Workshop on {NLP} for Music and Audio ({NLP}4{M}us{A} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nlp4musa-1.2/",
pages = "7--12",
ISBN = "979-8-89176-369-2",
abstract = "The advancement of Machine learning (ML), Large Audio Language Models (LALMs), and autonomous AI agents in Music Information Retrieval (MIR) necessitates a shift from static tagging to rich, human-aligned representation learning. However, the scarcity of open-source infrastructure capable of capturing the subjective nuances of audio annotation remains a critical bottleneck. This paper introduces LabelBuddy, an open-source collaborative auto-tagging audio annotation tool designed to bridge the gap between human intent and machine understanding. Unlike static tools, it decouples the interface from inference via containerized backends, allowing users to plug in custom models for AI-assisted pre-annotation. We describe the system architecture, which supports multi-user consensus, containerized model isolation, and a roadmap for extending agents and LALMs. Code available at https://github.com/GiannisProkopiou/gsoc2022-Label-buddy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prokopiou-etal-2026-labelbuddy">
<titleInfo>
<title>LabelBuddy: An Open Source Music and Audio Language Annotation Tagging Tool Using AI Assistance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Prokopiou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Sina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agisilaos</namePart>
<namePart type="family">Kounelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pantelis</namePart>
<namePart type="family">Vikatos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Themos</namePart>
<namePart type="family">Stafylakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on NLP for Music and Audio (NLP4MusA 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Epure</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergio</namePart>
<namePart type="family">Oramas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">SeungHeon</namePart>
<namePart type="family">Doh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Ramoneda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kruspe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Sordo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-369-2</identifier>
</relatedItem>
<abstract>The advancement of Machine learning (ML), Large Audio Language Models (LALMs), and autonomous AI agents in Music Information Retrieval (MIR) necessitates a shift from static tagging to rich, human-aligned representation learning. However, the scarcity of open-source infrastructure capable of capturing the subjective nuances of audio annotation remains a critical bottleneck. This paper introduces LabelBuddy, an open-source collaborative auto-tagging audio annotation tool designed to bridge the gap between human intent and machine understanding. Unlike static tools, it decouples the interface from inference via containerized backends, allowing users to plug in custom models for AI-assisted pre-annotation. We describe the system architecture, which supports multi-user consensus, containerized model isolation, and a roadmap for extending agents and LALMs. Code available at https://github.com/GiannisProkopiou/gsoc2022-Label-buddy.</abstract>
<identifier type="citekey">prokopiou-etal-2026-labelbuddy</identifier>
<location>
<url>https://aclanthology.org/2026.nlp4musa-1.2/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>7</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LabelBuddy: An Open Source Music and Audio Language Annotation Tagging Tool Using AI Assistance
%A Prokopiou, Ioannis
%A Sina, Ioannis
%A Kounelis, Agisilaos
%A Vikatos, Pantelis
%A Stafylakis, Themos
%Y Epure, Elena V.
%Y Oramas, Sergio
%Y Doh, SeungHeon
%Y Ramoneda, Pedro
%Y Kruspe, Anna
%Y Sordo, Mohamed
%S Proceedings of the 4th Workshop on NLP for Music and Audio (NLP4MusA 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-369-2
%F prokopiou-etal-2026-labelbuddy
%X The advancement of Machine learning (ML), Large Audio Language Models (LALMs), and autonomous AI agents in Music Information Retrieval (MIR) necessitates a shift from static tagging to rich, human-aligned representation learning. However, the scarcity of open-source infrastructure capable of capturing the subjective nuances of audio annotation remains a critical bottleneck. This paper introduces LabelBuddy, an open-source collaborative auto-tagging audio annotation tool designed to bridge the gap between human intent and machine understanding. Unlike static tools, it decouples the interface from inference via containerized backends, allowing users to plug in custom models for AI-assisted pre-annotation. We describe the system architecture, which supports multi-user consensus, containerized model isolation, and a roadmap for extending agents and LALMs. Code available at https://github.com/GiannisProkopiou/gsoc2022-Label-buddy.
%U https://aclanthology.org/2026.nlp4musa-1.2/
%P 7-12
Markdown (Informal)
[LabelBuddy: An Open Source Music and Audio Language Annotation Tagging Tool Using AI Assistance](https://aclanthology.org/2026.nlp4musa-1.2/) (Prokopiou et al., NLP4MusA 2026)
ACL