Alonso-Jiménez, PabloBogdanov, DmitryPons Puig, JordiSerra, Xavier2021-02-122020Alonso-Jiménez P, Bogdanov D, Pons J, Serra X. Tensorflow audio models in Essentia. In: 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP); 2020 May 4-8; Barcelona, Spain. New Jersery: The Institute of Electrical and Electronics Engineers; 2020. p. 266-70. DOI: 10.1109/ICASSP40776.2020.90546882379-190Xhttp://hdl.handle.net/10230/46455Comunicació presentada a: ICASSP 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, celebrat en línia del 4 al 8 de maig de 2020.Essentia is a reference open-source C ++ /Python library for audio and music analysis. In this work, we present a set of algorithms that employ TensorFlow in Essentia, allow predictions with pre-trained deep learning models, and are designed to offer flexibility of use, easy extensibility, and real-time inference. To show the potential of this new interface with TensorFlow, we provide a number of pre-trained state-of-the-art music tagging and classification CNN models. We run an extensive evaluation of the developed models. In particular, we assess the generalization capabilities in a cross-collection evaluation utilizing both external tag datasets as well as manual annotations tailored to the taxonomies of our models.application/pdfeng© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/10.1109/ICASSP40776.2020.9054688info:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1109/ICASSP40776.2020.9054688Music information retrievalMusic taggingDeep learningTransfer learningAudio analysis softwareinfo:eu-repo/semantics/openAccess