
Essentia MTG
@essentia_mtg
Open-source C++/Python library and AI models for audio and music analysis developed by @mtg_upf. Wrapper library for JS.
ID: 4526702794
http://essentia.upf.edu 18-12-2015 17:04:42
35 Tweet
270 Followers
0 Following

Having ported Essentia MTG to JS, it is now possible to run our algorithms for automated detection of audio problems in the browser. (🚀Pablo Alonso Jiménez, Albin Andrew Correya) More details in a hands-on workshop by Luis Joglar presented on Sónar+D. 👏 youtube.com/watch?v=NR9-hV…

Welcome to MIR in the browser as we present Essentia.js at @ismir2020! It is a wrapper JS library for Essentia with many music audio analysis algorithms. Join our poster for details and web demos. program.ismir2020.net/poster_4-18.ht… Dev work by Albin Andrew Correya, benchmarking by Luis Joglar.


Run music audio classification and auto-tagging in the browser! As we continue working on Essentia.js, we incorporated inference with TensorFlow models available in Essentia. See our paper with Albin Andrew Correya, Pablo Alonso Jiménez and @MaferGeorge for #WAC2021: webaudioconf2021.com/paper-c-4/

Pre-trained TensorFlow JS models for audio/music analysis, directly integrated into Essentia.js Essentia MTG. MIR on browsers 🎉 WAC2022 Check out webaudioconf2021.com/paper-c-4/ Joint-work with Dmitry Bogdanov Pablo Alonso Jiménez @MaferGeorge Xavier Serra Luis Joglar MTG-UPF

Glad to share that we got one of the best paper award at the Web Audio Conference 2021 WAC2022 :) Paper: webaudioconf2021.com/paper-c-4/ Joint work with Pablo Alonso Jiménez @MaferGeorge Xavier Serra Dmitry Bogdanov MTG-UPF


Learn the possibilities of music audio analysis in the browser using Essentia.js in this hands-on tutorial we did with Albin Andrew Correya, @MaferGeorge, and Luis Joglar a few months ago for WAC2022 #WAC2021. Slides: github.com/MTG/essentia.j… youtube.com/watch?v=p23DfQ…


Onset detection in your browser with Essentia.js. Load any audio file or choose audio from Freesound and start slicing! Click on segments to preview and tune detection parameters. You can then download your results. Demo by Jorge Marcos MTG-UPF. 🎶🍴🎶 mtg.github.io/essentia.js/ex…

Slice any audio directly in your browser with onset detection from Essentia.js. Create weighted combinations of onset detection functions for different segmentation results. Works best with short audio clips. Demo built by Jorge Marcos at MTG-UPF. 🎶🔪🎶 mtg.github.io/essentia.js/ex…

✍️New model out✍️ MAEST is an open music representation model trained in music style classification. 🎙️Conf: Accepted in #ISMIR2023 📄Paper: hdl.handle.net/10230/58023 💻Code: github.com/palonso/MAEST ⚙️Essentia: essentia.upf.edu/models.html#ma… 🤗 HF: huggingface.co/mtg-upf 🧵👇 [1/6]

We've updated Essentia with a new music representation model based on transformers and trained on music style metadata in Discogs. Useful for genre classification (400 styles) and downstream auto-tagging tasks. This work, led by Pablo Alonso Jiménez, will be presented at #ISMIR2023 👇



I am happy to announce that we'll be presenting our music analysis software and AI models Essentia MTG and related activities of MTG-UPF at the Sónar 2024 Project Area, June 13 to 15. Sónar Festival Sónar+D 🔊⚡ w/ Pablo Alonso Jiménez, Jorge Marcos
