Deep embeddings with Essentia models

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Alonso-Jiménez, Pablo
• dc.contributor.author Bogdanov, Dmitry
• dc.contributor.author Serra, Xavier
• dc.date.accessioned 2020-10-09T07:34:46Z
• dc.date.available 2020-10-09T07:34:46Z
• dc.date.issued 2020
• dc.description Comunicació presentada a: International Society for Music Information Retrieval Conference celebrat de l'11 al 16 d'octubre de 2020 de manera virtual.
• dc.description.abstract We present the integration of various CNN TensorFlow models developed for different MIR tasks into Essentia. This is a continuation of our previous work [1], extending the list of supported models and adding new algorithms to facilitate usability. Essentia provides input feature extraction and inference with TensorFlow models in a single C++ pipeline with Python bindings, facilitating the deployment of C++ and Python MIR applications. We assess the new models’ capabilities to serve as embedding extractors in many downstream classification tasks. All presented models are publicly available on the Essentia website.
• dc.format.mimetype application/pdf
• dc.identifier.citation Alonso-Jiménez P, Bogdanov D, Serra X. Deep embeddings with Essentia models. Paper presented at: International Society of Music Information Retrieval Conference (ISMIR); 2020 Oct 11-16; Montréal, Canada.
• dc.identifier.uri http://hdl.handle.net/10230/45452
• dc.language.iso eng
• dc.publisher ISMIR
• dc.rights Licensed under a Creative Commons Attribution 4.0 In- ternational License (CC BY 4.0). 21st International Society for Music Information Retrieval Conference, Montréal, Canada, 2020.
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri https://creativecommons.org/licenses/by/4.0/
• dc.title Deep embeddings with Essentia models
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion