Renaissance Labs

Atlas / Europe

Academic lab · Barcelona, Spain

Music Technology GroupUPF

The Barcelona research group behind Essentia and Freesound-linked work, building open audio and music analysis software since 1994.

music AIaudio analysis

Barcelona, Spain

Founded
1994
Type
Academic lab
Based in
Barcelona, Spain
Featured projects
4

About

The Music Technology Group is a research group of the Department of Information and Communication Technologies at Universitat Pompeu Fabra in Barcelona. It was founded in 1994 by Xavier Serra, who still directs it.

Its research covers audio signal processing, sound and music description, musical interaction, and sound and music communities. The group releases much of its software as open source on GitHub.

Its best known software is Essentia, a C++ library with Python bindings for audio analysis and music information retrieval. The library began in 2006 to replace a set of ad hoc C++ programs and is released under the AGPLv3 licence.

Mission and ambitions

The group works to advance sound and music computing and to turn that research into open tools used by scientists, developers and artists.

Known for

  1. 01

    Essentia audio analysis library

  2. 02

    Founded 1994 by Xavier Serra

  3. 03

    Sound and music computing research

  4. 04

    Open music information retrieval datasets and tools

Milestones

  1. 1994

    MTG founded

    Xavier Serra founded the group at Universitat Pompeu Fabra.

  2. 2006

    Essentia development begins

    Started to replace ad hoc C++ programs used inside the group.

  3. 2008

    Essentia 1.0

    First numbered release of the library, per Essentia documentation.

  4. 2013

    Essentia paper at ACM Multimedia

    Bogdanov and colleagues presented the open-source library at MM'13.

Open source

GitHubgithub.com/MTG
  • C++ library for audio and music analysis, description and synthesis, including Python bindings (3,808 stars)

  • Sound analysis/synthesis tools for music applications (1,801 stars)

  • JavaScript library for music/audio analysis and processing powered by Essentia WebAssembly (874 stars)

  • Deep Convolutional Neural Networks for Musical Source Separation (484 stars)

Notable releases

Openness

Libraries and research code are public on GitHub; Essentia is released as open source (AGPL with commercial licences available).

People

Listed from the lab's own pages and public profiles.

Contact and community

Contact through the website.

Sources

Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.

Labs nearby