Technologies - Essentia
Back Technologies - Essentia
Software library and AI models containing an extensive collection of reusable algorithms for audio and music analysis, description, and synthesis. Designed to support large-scale industrial applications.
Essentia is the result of more than 10 years of research at the MTG on audio signal processing and music information retrieval, incorporating the work done by many researchers during all this time. It is maintained and used by a very active team of researchers and developers.
Essentia is a C++ library with Python bindings for audio analysis, description, and synthesis. The library contains an extensive collection of reusable algorithms which implement audio input/output functionality, standard digital signal processing blocks, statistical characterization of data, and a large set of spectral, temporal, tonal and high-level music descriptors. Essentia is cross-platform and it is designed with a focus on optimization in terms of robustness, computational speed and low memory usage, which makes it effective for many industrial applications. The library is also wrapped in Python and includes a number of command-line tools and third-party extensions, which facilitate its use for fast development.
Field / topics
Music Information Retrieval, Audio Signal Processing, Music Recomendation, ....
Essentia is being used to support tasks such as audio similarity, music classification, semantic autotagging, mood detection, key detection, onset detection, segmentation, beat tracking, melody extraction, audio fingerprinting, spectral analysis, loudness metering, or sound synthesis. These tasks are at the core of applications such as music recommendation, visualization and interaction with music, sound indexing, musical instruments detection, or cover detection. Example applications of Essentia are described in the website.
The Essentia library is wrapped in Python and includes a number of command-line tools and third-party extensions, which facilitate its use in fast prototyping and software development. Essentia is available under an open licence, Affero GPL, for non commercial applications, thus it is possible to test the library before deciding to licence it for commercial use. There is a large community of researchers using Essentia and contributing to it, thus it is constantly being updated and improved.
TRL 8. The library has been used and tested in real industrial applications.
Commercial license for embedding Essentia in other software applications. We licence the complete library or specific algorithms. Details of the license are in the website. We also offer support services to adapt and integrate Essentia into particular applications.
For an extensive documentation of Essentia or for downloading it for evaluation purposes, go to http://essentia.upf.edu.
For any further information or licensing inquiries contact us.