ESSENTIA: an open source library for audio analysis

Dmitry Bogdanov, Nicolas Wack, Emilia Gómez, Sankalp Gulati, Perfecto Herrera, Oscar Mayor, Gerard Roma, Justin Salamon, José Zapata, Xavier Serra

Research output: Contribution to specialist publicationArticle

Abstract

We present Essentia 2.0, an open-source C++ library for
audio analysis and audio-based music information retrieval
released under the Affero GPL license. It 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. The library is also wrapped in Python and includes a
number of predefined executable extractors for the available
music descriptors, which facilitates its use for fast prototyping and allows setting up research experiments very rapidly.
Furthermore, it includes a Vamp plugin to be used with
Sonic Visualiser for visualization purposes. The library is
cross-platform and currently supports Linux, Mac OS X,
and Windows systems. Essentia is designed with a focus on
the robustness of the provided music descriptors and is optimized in terms of the computational cost of the algorithms.
The provided functionality, specifically the music descriptors included in-the-box and signal processing algorithms, is
easily expandable and allows for both research experiments
and development of large-scale industrial applications.
LanguageEnglish
Pages18-21
Number of pages4
Volume6
No.1
Specialist publicationACM SIGMM Records
Publication statusPublished - Mar 2014
Externally publishedYes

Fingerprint

Digital signal processing
Industrial applications
Signal processing
Visualization
Costs
Experiments
Linux

Cite this

Bogdanov, D., Wack, N., Gómez, E., Gulati, S., Herrera, P., Mayor, O., ... Serra, X. (2014). ESSENTIA: an open source library for audio analysis. ACM SIGMM Records, 6(1), 18-21.
Bogdanov, Dmitry ; Wack, Nicolas ; Gómez, Emilia ; Gulati, Sankalp ; Herrera, Perfecto ; Mayor, Oscar ; Roma, Gerard ; Salamon, Justin ; Zapata, José ; Serra, Xavier. / ESSENTIA : an open source library for audio analysis. In: ACM SIGMM Records. 2014 ; Vol. 6, No. 1. pp. 18-21.
@misc{b7363cabe2d34344a2d8bbbcce49648c,
title = "ESSENTIA: an open source library for audio analysis",
abstract = "We present Essentia 2.0, an open-source C++ library foraudio analysis and audio-based music information retrievalreleased under the Affero GPL license. It contains an extensive collection of reusable algorithms which implement audioinput/output functionality, standard digital signal processing blocks, statistical characterization of data, and a largeset of spectral, temporal, tonal and high-level music descriptors. The library is also wrapped in Python and includes anumber of predefined executable extractors for the availablemusic descriptors, which facilitates its use for fast prototyping and allows setting up research experiments very rapidly.Furthermore, it includes a Vamp plugin to be used withSonic Visualiser for visualization purposes. The library iscross-platform and currently supports Linux, Mac OS X,and Windows systems. Essentia is designed with a focus onthe robustness of the provided music descriptors and is optimized in terms of the computational cost of the algorithms.The provided functionality, specifically the music descriptors included in-the-box and signal processing algorithms, iseasily expandable and allows for both research experimentsand development of large-scale industrial applications.",
keywords = "Open Source, Signal Processing, Audio Analysis, Music Information Retrieval, Sound and music computing",
author = "Dmitry Bogdanov and Nicolas Wack and Emilia G{\'o}mez and Sankalp Gulati and Perfecto Herrera and Oscar Mayor and Gerard Roma and Justin Salamon and Jos{\'e} Zapata and Xavier Serra",
year = "2014",
month = "3",
language = "English",
volume = "6",
pages = "18--21",
journal = "ACM SIGMM Records",
issn = "1947-4598",

}

Bogdanov, D, Wack, N, Gómez, E, Gulati, S, Herrera, P, Mayor, O, Roma, G, Salamon, J, Zapata, J & Serra, X 2014, 'ESSENTIA: an open source library for audio analysis' ACM SIGMM Records, vol. 6, no. 1, pp. 18-21.

ESSENTIA : an open source library for audio analysis. / Bogdanov, Dmitry; Wack, Nicolas; Gómez, Emilia; Gulati, Sankalp; Herrera, Perfecto; Mayor, Oscar; Roma, Gerard; Salamon, Justin; Zapata, José; Serra, Xavier.

In: ACM SIGMM Records, Vol. 6, No. 1, 03.2014, p. 18-21.

Research output: Contribution to specialist publicationArticle

TY - GEN

T1 - ESSENTIA

T2 - ACM SIGMM Records

AU - Bogdanov, Dmitry

AU - Wack, Nicolas

AU - Gómez, Emilia

AU - Gulati, Sankalp

AU - Herrera, Perfecto

AU - Mayor, Oscar

AU - Roma, Gerard

AU - Salamon, Justin

AU - Zapata, José

AU - Serra, Xavier

PY - 2014/3

Y1 - 2014/3

N2 - We present Essentia 2.0, an open-source C++ library foraudio analysis and audio-based music information retrievalreleased under the Affero GPL license. It contains an extensive collection of reusable algorithms which implement audioinput/output functionality, standard digital signal processing blocks, statistical characterization of data, and a largeset of spectral, temporal, tonal and high-level music descriptors. The library is also wrapped in Python and includes anumber of predefined executable extractors for the availablemusic descriptors, which facilitates its use for fast prototyping and allows setting up research experiments very rapidly.Furthermore, it includes a Vamp plugin to be used withSonic Visualiser for visualization purposes. The library iscross-platform and currently supports Linux, Mac OS X,and Windows systems. Essentia is designed with a focus onthe robustness of the provided music descriptors and is optimized in terms of the computational cost of the algorithms.The provided functionality, specifically the music descriptors included in-the-box and signal processing algorithms, iseasily expandable and allows for both research experimentsand development of large-scale industrial applications.

AB - We present Essentia 2.0, an open-source C++ library foraudio analysis and audio-based music information retrievalreleased under the Affero GPL license. It contains an extensive collection of reusable algorithms which implement audioinput/output functionality, standard digital signal processing blocks, statistical characterization of data, and a largeset of spectral, temporal, tonal and high-level music descriptors. The library is also wrapped in Python and includes anumber of predefined executable extractors for the availablemusic descriptors, which facilitates its use for fast prototyping and allows setting up research experiments very rapidly.Furthermore, it includes a Vamp plugin to be used withSonic Visualiser for visualization purposes. The library iscross-platform and currently supports Linux, Mac OS X,and Windows systems. Essentia is designed with a focus onthe robustness of the provided music descriptors and is optimized in terms of the computational cost of the algorithms.The provided functionality, specifically the music descriptors included in-the-box and signal processing algorithms, iseasily expandable and allows for both research experimentsand development of large-scale industrial applications.

KW - Open Source

KW - Signal Processing

KW - Audio Analysis

KW - Music Information Retrieval

KW - Sound and music computing

UR - http://records.mlab.no/

M3 - Article

VL - 6

SP - 18

EP - 21

JO - ACM SIGMM Records

JF - ACM SIGMM Records

SN - 1947-4598

ER -

Bogdanov D, Wack N, Gómez E, Gulati S, Herrera P, Mayor O et al. ESSENTIA: an open source library for audio analysis. ACM SIGMM Records. 2014 Mar;6(1):18-21.