@inproceedings{jajoria-etal-2026-audio,
title = "Audio-Lyrics Alignment Dataset for {I}talian Arias",
author = "Jajoria, Pushkar and
Graciotti, Arianna and
Casali, Giovanna and
Alabi, Jesujoba and
Delmonte, Rodolfo and
Pompilio, Angelo and
Tripodi, Rocco and
McDermott, James and
Klakow, Dietrich",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.454/",
doi = "10.63317/4cpveetxxtmx",
pages = "5757--5766",
abstract = "Aligning song lyrics with sung audio is challenging, especially for languages and music styles where annotated datasets are scarce. We address this gap by presenting the first dataset of Italian opera arias annotated with lyrics and time-stamps per word. The dataset comprises of 24 arias drawn from well-known operas of the 18th to 20th centuries with a total audio duration of nearly two hours. We benchmark both music alignment models and speech forced alignment models and show that existing methods face significant challenges on this dataset, with performance dropping by 45{\%} compared to other datasets. Multilingual and speech-based models exhibit relatively better performance on this dataset. We also evaluate few-shot fine-tuning of these models on the new dataset and find that, while it yields only marginal overall improvement, it produces localized gains on specific arias, suggesting that limited exposure helps the model adapt to some patterns but cannot fully overcome differences in language or musical style."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jajoria-etal-2026-audio">
<titleInfo>
<title>Audio-Lyrics Alignment Dataset for Italian Arias</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pushkar</namePart>
<namePart type="family">Jajoria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Graciotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanna</namePart>
<namePart type="family">Casali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodolfo</namePart>
<namePart type="family">Delmonte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angelo</namePart>
<namePart type="family">Pompilio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rocco</namePart>
<namePart type="family">Tripodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">McDermott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Klakow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Aligning song lyrics with sung audio is challenging, especially for languages and music styles where annotated datasets are scarce. We address this gap by presenting the first dataset of Italian opera arias annotated with lyrics and time-stamps per word. The dataset comprises of 24 arias drawn from well-known operas of the 18th to 20th centuries with a total audio duration of nearly two hours. We benchmark both music alignment models and speech forced alignment models and show that existing methods face significant challenges on this dataset, with performance dropping by 45% compared to other datasets. Multilingual and speech-based models exhibit relatively better performance on this dataset. We also evaluate few-shot fine-tuning of these models on the new dataset and find that, while it yields only marginal overall improvement, it produces localized gains on specific arias, suggesting that limited exposure helps the model adapt to some patterns but cannot fully overcome differences in language or musical style.</abstract>
<identifier type="citekey">jajoria-etal-2026-audio</identifier>
<identifier type="doi">10.63317/4cpveetxxtmx</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.454/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5757</start>
<end>5766</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Audio-Lyrics Alignment Dataset for Italian Arias
%A Jajoria, Pushkar
%A Graciotti, Arianna
%A Casali, Giovanna
%A Alabi, Jesujoba
%A Delmonte, Rodolfo
%A Pompilio, Angelo
%A Tripodi, Rocco
%A McDermott, James
%A Klakow, Dietrich
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F jajoria-etal-2026-audio
%X Aligning song lyrics with sung audio is challenging, especially for languages and music styles where annotated datasets are scarce. We address this gap by presenting the first dataset of Italian opera arias annotated with lyrics and time-stamps per word. The dataset comprises of 24 arias drawn from well-known operas of the 18th to 20th centuries with a total audio duration of nearly two hours. We benchmark both music alignment models and speech forced alignment models and show that existing methods face significant challenges on this dataset, with performance dropping by 45% compared to other datasets. Multilingual and speech-based models exhibit relatively better performance on this dataset. We also evaluate few-shot fine-tuning of these models on the new dataset and find that, while it yields only marginal overall improvement, it produces localized gains on specific arias, suggesting that limited exposure helps the model adapt to some patterns but cannot fully overcome differences in language or musical style.
%R 10.63317/4cpveetxxtmx
%U https://aclanthology.org/2026.lrec-1.454/
%U https://doi.org/10.63317/4cpveetxxtmx
%P 5757-5766
Markdown (Informal)
[Audio-Lyrics Alignment Dataset for Italian Arias](https://aclanthology.org/2026.lrec-1.454/) (Jajoria et al., LREC 2026)
ACL
- Pushkar Jajoria, Arianna Graciotti, Giovanna Casali, Jesujoba Alabi, Rodolfo Delmonte, Angelo Pompilio, Rocco Tripodi, James McDermott, and Dietrich Klakow. 2026. Audio-Lyrics Alignment Dataset for Italian Arias. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5757–5766, Palma de Mallorca, Spain. ELRA Language Resource Association.