Essentia: An Audio Analysis Library for Music Information Retrieval
By Dmitry Bogdanov, N. Wack, Emilia G'omez, Sankalp Gulati, Perfecto Herrera, Oscar Mayor, Gerard Roma, Justin Salamon, J. R. Zapata, Xavier Serra. International Society for Music Information Retrieval Conference, 2013
453 citations recorded by the source corpus.
View Paper: https://www.semanticscholar.org/paper/2259fe25b38783db2769e3e2f0000689e52d70ac
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Eduardo Fonseca
- Xavier Favory
- Xavier Serra
- Frederic Font
- Jordi Pons
- Andrés Ferraro
- Minz Won
- Jong Wook Kim
Citations in the corpus
- A Simple Fusion of Deep and Shallow Learning for Acoustic Scene Classification (2018, methodology): “1), while for the latter we used the Essentia implementation [15], which is in turn adapted from [16].”
- Acoustic Scene Classification by Ensembling Gradient Boosting Machine and Convolutional Neural Networks (2017, methodology): “We then extract features on each sequence using FreesoundExtractor,(3) a feature extractor from Essentia open-source library for audio analysis [17].”
- Evaluation of CNN-based Automatic Music Tagging Models (2020, methodology): “Essentia [18] and Librosa [19] libraries are used for loading audio files and extracting Mel spec-trograms, respectively.”
- Freesound Datasets: A Platform for the Creation of Open Audio Datasets (2017, methodology): “In addition, audio features 13 pre-computed with the Essentia library [3] are available.”
- Open-Source Practices for Music Signal Processing Research: Recommendations for Transparent, Sustainable, and Reproducible Audio Research (2019, background): “Many open-source libraries exist for audio feature extraction, such as Essentia [23], librosa [24], aubio [25], Madmom [26], or Marsyas [27].”
- Search Result Clustering in Collaborative Sound Collections (2020, methodology): “One set of manually selected features motivated from the literature (F1) [11, 18, 23, 31, 41], another set contains all of the lowlevel features available from the Essentia Freesound Extractor (F2) [4], and the third one uses embeddings from a neural network model trained on AudioSet [17, 19] (F3).”