Digital Humanities · Music · AI

CAPTAL-LAB

// Xavier Fresquet — SCAI · Sorbonne Abu Dhabi

A lab where medieval chant manuscripts meet large language models, where Renaissance polyphony gets a GPU, and where the boundary between musicologist and ML engineer has long since evaporated.

Captal — from Old Gascon capitalis, "chief lord". A medieval feudal title in Gascony, immortalized by Jean Froissart in his Chronicles as the Captal de Buch, champion of the Black Prince. The name came back during a White Rose Fellowship in Sheffield, where I first read Froissart. It stuck.

01

About

Xavier Fresquet
Xavier Fresquet
Director, SCAI Abu Dhabi
Deputy Director, SCAI Paris
Musicologist · DH Researcher
Sorbonne Abu Dhabi 🇦🇪

I'm a musicologist who became suspicious of computers early on, then couldn't stop. Trained at Bordeaux Montaigne and Sorbonne, I did a PhD in Music & Digital Humanities (2011), with research stays at the University of Sheffield (White Rose Scholarship), Brown University, UC Berkeley, and a sabbatical year at UWA in Perth that confirmed: no matter how far you go, you're still thinking about medieval manuscripts.

Back in Paris, I co-founded SCAI — the Sorbonne Center for Artificial Intelligence — alongside mathematician Gérard Biau. Running SCAI meant organizing a few hundred seminars, managing European grants across three languages, and convincing a lot of scientists that the humanities might actually have something useful to say about AI.

In February 2026, I moved to Abu Dhabi to become Director of SCAI at Sorbonne Abu Dhabi. The lab followed. The medieval sources did not, but the servers talk to Eurasia just fine over SSH.

The CAPTAL Lab is where I house everything: AI models for music generation, computational musicology, open datasets, DH tools, and the occasional philosophical detour into AI ethics. The name stands for Computational Analysis of Polyphonic and Traditional Artworks Lab — which nobody actually says out loud.

Academic Background

2026 →
Director, SCAI Abu Dhabi · Sorbonne Abu Dhabi (SUAD)
2020 →
Deputy Director, SCAI · Sorbonne Université, Paris
2014–15
Sabbatical · UWA, Notre Dame & Curtin, Perth
2009–14
Deputy Head, International Publications · Campus France
2007–09
White Rose PhD Scholarship · University of Sheffield (Online Froissart Project)
2007
Research Fellowship · Brown University, Providence
2004
EAP Fellowship · UC Berkeley
2011
PhD Music & Musicology (DH) · Sorbonne & Bordeaux Montaigne

Research Areas

Computational Musicology Medieval Music Generative AI / LLM Renaissance Polyphony Music Iconography Digital Heritage NLP for Music Style Transfer Dataset Construction Baroque Sacred Music Fugue Analysis AI Ethics Open Science Soundscape Studies

Selected Grants

ANR MELODY 2026–2030 (PI) POSTGENAI@PARIS — 35M€ SOUND.AI MSCA COFUND — 5.3M€ PRESTIGE MSCA COFUND — 15M€ MAESTRIA Horizon Europe — 14M€ ANR Musiconis — 350k€ LabEx PLAS@PAR — 7.5M€
02

Research Projects

Symbolic Music Dataset Active

HARMONIA Dataset

A large-scale symbolic music corpus spanning roughly five centuries, with harmonic annotations. The pipeline runs on an HPC cluster named Eurasia. It is cooking. We check on it regularly.

Gemma Music Generation Active

GEMMA-PDMX

Fine-tuning Gemma on French Baroque polyphony (think Charpentier, lots of it) with preference-based alignment. Multiple training phases, each more elaborately named than the last. Results pending, spirits high.

Reasoning LLM Active

MUSIC-REASONING / ZR1

Can a small language model reason through counterpoint? We're building chain-of-thought reasoning traces from music theory treatises and fine-tuning DeepSeek-R1. It thinks before it writes notes. Very à la mode.

Transformer Diffusion Active

Hybrid-Model

A tripartite Transformer + Diffusion + VAE architecture for symbolic music generation. Soprano inpainting: done. The model has been running on Eurasia long enough to know the cluster's maintenance schedule.

Phonology Latin Ready to submit

Soundscapes of Authority

Computational philology of Latin music performance terminology. ~5,200 words, a full NLP pipeline, and more ablative absolutes than strictly necessary. Targeting Digital Humanities Quarterly.

Dataset Published

CSMD — Charpentier Sacred Music

52 sacred works by Marc-Antoine Charpentier, annotated and published on Zenodo (DOI: 10.5281/zenodo.20450425). CITATION.cff, full metadata, multi-format. It's out there. Properly.

Style Transfer Live

Charpentier 4-Voice Transfer

Gradio app for Baroque style transfer: feed it a melody, get back something that sounds vaguely like Charpentier. Powered by a fine-tuned NotaGen. Running locally on port 8012. Works surprisingly often.

Knowledge Graph SKOS Active

Euterpe Knowledge Graph

Transforming the Euterpe iconographic database into a proper RDF/SKOS knowledge graph, with a data paper and migration pipeline into Musiconis (~1,000 medieval records). Unglamorous, essential.

Lexicon 19th c. Final review

Lexicon C19

A structured lexicon of 19th-century music performance terminology, pulling from French, German (Meyers — yes, the whole thing), and English sources. 3,760 entries. Zenodo deposit imminent.

Medieval Chant Ready

Cantus Extra Librum

On plainchant that happens outside the book — informal, contextual, sung without a score. Article complete, titled "Bizarrifying the Past", targeting Filigrane. Related to a November 2025 cathedral concert.

Fugue Testing Phase 5

FugueTest

145 automated tests covering fugue exposition detection, subject/answer identification, and voice-leading validation. Phases 0–4 complete. Bach would still find something to complain about.

Organology Cladistics In review

PhyloGenie Harp

Applying phylogenetic and cladistic methods to the morphological evolution of the medieval harp via the Musiconis dataset. With Edmundo Camacho (UNAM). Article in co-author review, targeting Cahiers d'ethnomusicologie.

Gemma LoRA Done

Gemma-Renaissance

LoRA fine-tuning of Gemma on Renaissance polyphony. Training completed on Eurasia (~5h). The adapter exists; it sounds like it read Josquin but is unsure about Palestrina.

RAG Musicology Prototype

RAG MusiSorbonne

A retrieval-augmented generation assistant over the MusiSorbonne archival corpus. Useful for navigating large, heterogeneous musicological archives. Prototype running; article drafted.

03

ANR MELODY

ANR · TSIA · 2026–2030 · Principal Investigator

Music, Encoding, Learning, Data
and Open pOlYphony

A four-year French national research project (Agence Nationale de la Recherche) on AI and music. The core question: can machines learn to understand music the way a trained musician does — not just pattern-match, but reason about counterpoint, style, and structure? We're building the models, the datasets, and the evaluation tools to find out. We'll be at this for a while. Good.

MELODY covers four interconnected research tracks, all running in parallel on the CAPTAL-LAB infrastructure (local machines + Eurasia GPU cluster). The target output: open datasets, reproducible models, and a substantial contribution to the ISMIR community. 2026 is just the start.

TRACK A · Datasets

HARMONIA

A large-scale symbolic music corpus spanning five centuries with harmonic annotations. Pipeline running on Eurasia. ~5,000 pieces expected. The infrastructure for everything else.

TRACK B · Generation

GEMMA-PDMX & Hybrid-Model

Two parallel approaches to symbolic music generation: a fine-tuned Gemma with preference alignment on French Baroque polyphony, and a Transformer+Diffusion+VAE tripartite architecture for soprano inpainting and conditioned generation.

TRACK C · Reasoning

MUSIC-REASONING / ZR1

Can a small language model reason through counterpoint? Chain-of-thought traces from music theory treatises, fine-tuning DeepSeek-R1 on voice-leading tasks. The model thinks before it writes notes. TISMIR target.

TRACK D · Infrastructure

melody-forge & PDMX Explorer

Open-source toolchain for symbolic music ingestion, conversion, and analysis. Drop a score file in; get ABC, MusicXML, AST, and AI-driven musicological analysis out. Freely available on GitHub and HAL.

OPEN SCIENCE All MELODY datasets, models, and tools are released openly — Zenodo, HAL, GitHub. The project runs on the conviction that computational musicology advances faster when the infrastructure is shared.
04

Abu Dhabi — Sorbonne 🇦🇪

Since February 2026, CAPTAL-LAB has a Gulf outpost. As Director of SCAI at Sorbonne Abu Dhabi, the research agenda has expanded to include Gulf soundscapes, local heritage digitisation, and Year of AI 2026 coordination. The timezone is challenging; the light is not.

Seminar Series IoT · AI Active

AI Garden

A DH seminar series at SUAD — informal by design, more garden table than podium. Topics move between AI methods, heritage data, and questions without clean answers yet. The project has a physical dimension: students are building an AI-managed garden on campus, with soil sensors and a Ma Hawa atmospheric water generator — a machine that makes water from air. In Abu Dhabi, that's not a metaphor.

Ethnomusicology Urban Studies Ready to submit

Sonic Topographies of Abu Dhabi

Computational and ethnomusicological study of migrant musical worlds, cultural policy, and sonic space in Abu Dhabi. 175 entries, full draft complete. Targeting Ethnomusicology / Music & Politics.

Archive Prototype live

Abu Dhabi Soundscape Archive

A web application archiving and spatialising soundscape recordings from Abu Dhabi. Prototype operational. The data paper and Zenodo deposit are in progress. Listening to cities as data.

Web Radio Ongoing

SUAD-Radio

A web radio project for Sorbonne Abu Dhabi. Because a university should have a radio station, and someone should make playlists that algorithmically transition from Lassus to Mohamed Abdo without warning.

Big Science · AI Policy Speculative

A CERN for AI

A slightly crazy idea, full of hope. CERN brought nations together around a particle accelerator and kept channels open across the Iron Curtain. What if Abu Dhabi — crossroads between blocs, acceptable to all sides — hosted a neutral public institution for frontier AI: open science, shared evaluation, safety research, and fellows from the Global South? Not a think-tank. An instrument. A paper is being written; the argument is more serious than it sounds.

Digital Humanities Web Archive Emerging

WebRescue — DH Lab for the Disappearing Web

An idea from Sophia Mahroug: a Digital Humanities lab focused on archiving censored and vanishing web content — legislation behind geofences, blogs erased after regime change, state sites rewritten in silence. Beyond preservation, a space to bring the DH community in Abu Dhabi together around shared tools, methods, and questions that matter. A seminar, a lab, and — if we get the timing right — a research project.

05

Collaborators

These are people I work with, have worked with for a long time, and genuinely like. Frédéric Billiet (Paris-Sorbonne) has been my closest collaborator in medieval musicology for over a decade — co-creator of Musiconis, and the kind of colleague whose rigour makes the computational experiments feel honest. Gérard Biau (Sorbonne) co-founded SCAI with me and has the rare quality of making a mathematician and a medievalist feel like they're working on the same problem.

Susan Boynton (Columbia) brought a wonderful chant scholarship perspective to the Musiconis project. Jérôme Nika (IRCAM) thinks about AI and musical creativity in ways I find consistently inspiring. Valérie Nunes-Le Page navigates the border between music, AI, and artistic practice with real elegance. Fouad Aouinti and Victoria Eyharabide (both at LIP6/Sorbonne) have been great collaborators on deep learning and medieval image analysis. Motasem Alrahabi and Pierre-Marie Chauvin (Sorbonne) are colleagues whose paths keep crossing mine in the best ways.

Edmundo Camacho (UNAM) spent 2024–2025 applying phylogenetics to medieval harps, which is exactly as interesting as it sounds. Sabrina Moura (UNICAMP) collaborated on the Arabian Gulf DH project — a genuinely stimulating collective effort. Ana Amorim dragged me into a beautiful project about mental maps and urban memory, Unwalked Days, which I'm glad she did.

In Abu Dhabi: David Wrisley (NYU Abu Dhabi) is the kind of DH interlocutor you hope to find when you land in a new city. Proscovia Svärd and Lama Tarsissi (SUAD) make the day-to-day research life here genuinely good. And Louvre Abu Dhabi has been an open and generous partner for thinking about AI and cultural heritage in the Gulf.

06

Publications & Datasets

A selection of recent output — articles, preprints, and open datasets. For the full picture, see my HAL page.

Articles

2025
Representations of Sound and Music in the Middle Ages: Analysis and Visualization of the Musiconis Database
Journal of the American Musicological Society
Camacho, E., Fresquet, X. & Billiet, F. · HAL hal-05527559
2024
Seeing Sound: Visual Representations of Music in Medieval Iconography Using the Musiconis Database
Musica & Figura
Camacho, E., Fresquet, X. & Billiet, F. · HAL hal-05524401
2024
Artificial Neural Networks and Medieval Music
Early Music, vol. 52(3), pp. 298–317 — Oxford University Press
Fresquet, X.
2025
Feeling Machines: Ethics, Culture, and the Rise of Emotional AI
arXiv:2506.12437 · HAL hal-05549814
Chavan, V., Cenaj, A., Fresquet, X. et al.
2025
AI and Digital Humanities in the Arabian Gulf: Interdisciplinary Perspectives on Infrastructure, Cultural Heritage, and Community Building
Intelligence artificielle et humanités numériques dans le Golfe arabo-persique
Catelan, N., Fresquet, X., Moura, S., Svärd, P. & Wrisley, D.J.
2025
SIMMI: Synthetic Images for Medieval Musical Iconography
Conference paper
Picascia, S., Aouinti, F., Fresquet, X. & Billiet, F.
2025
Structured Knowledge Frameworks for Musicological AI Applications
ISMIR 2025, Daejeon
Fresquet, X.
2022
Illumination Detection in IIIF Medieval Manuscripts Using Deep Learning
Digital Medievalist, 15(1)
Aouinti, F., Eyharabide, V., Fresquet, X. & Billiet, F.
2020
L'iconographie musicale ancienne à la lumière des technologies sémantiques
Book chapter · HAL: hal-02542056
Fresquet, X.
2010
Musicastallis: Base de données des scènes musicales dans les stalles médiévales
in W. Muller, La nature, rythme et danse des saisons dans les stalles médiévales, Brepols
Fresquet, X.

Preprints & Reports (HAL)

2026
Mapping Medieval Musicology in the Age of Open Data: A Critical Bibliometric Analysis Using OpenAlex
HAL hal-05608871
Fresquet, X.
2025
Exploring PDMX as a Digital Humanities Observatory of Symbolic Music
HAL hal-05605863
Fresquet, X.
2025
Semantic History of Medieval Music: A Wikidata Framework for Computational Historiography
HAL hal-05361112
Fresquet, X.

Datasets & Software (Zenodo / HAL)

2026
Charpentier Sacred Music Dataset (CSMD v1.0)
Zenodo — DOI: 10.5281/zenodo.20450425
Fresquet, X. · Dataset + Notebook
2026
melody-forge — Symbolic Music Toolchain
HAL hal-05638223
Fresquet, X. · Software
2026
PDMX Explorer — DH Framework for Symbolic Music Datasets
HAL hal-04538223
Fresquet, X. · Software + Report
2026
Redefining AutoML for the Digital Humanities
HAL hal-04538224
Fresquet, X.
2025
Representations of Sound and Music in the Middle Ages — Musiconis Visualization Dataset
Zenodo — DOI: 10.5281/ZENODO.15037823
Fresquet, X. · Dataset
20+
Active Projects AI models, datasets, articles, tools
553
Scientific Events Organized At SCAI, 2020–2026
100M+
€ in Grants Managed ANR, Horizon Europe, MSCA…
Medieval Sources Musiconis, Cantus, Euterpe…