101575 20230519145435.0 doi 10.3390/electronics10070810 sideral 123846 ART-2021-123846 eng Hernández-Oliván, Carlos Universidad de Zaragoza (orcid)0000-0002-0235-2267 A Comparison of Deep Learning Methods for Timbre Analysis in Polyphonic Automatic Music Transcription 2021 Access copy available to the general public Unrestricted Automatic music transcription (AMT) is a critical problem in the field of music information retrieval (MIR). When AMT is faced with deep neural networks, the variety of timbres of different instruments can be an issue that has not been studied in depth yet. The goal of this work is to address AMT transcription by analyzing how timbre affect monophonic transcription in a first approach based on the CREPE neural network and then to improve the results by performing polyphonic music transcription with different timbres with a second approach based on the Deep Salience model that performs polyphonic transcription based on the Constant-Q Transform. The results of the first method show that the timbre and envelope of the onsets have a high impact on the AMT results and the second method shows that the developed model is less dependent on the strength of the onsets than other state-of-the-art models that deal with AMT on piano sounds such as Google Magenta Onset and Frames (OaF). Our polyphonic transcription model for non-piano instruments outperforms the state-of-the-art model, such as for bass instruments, which has an F-score of 0.9516 versus 0.7102. In our latest experiment we also show how adding an onset detector to our model can outperform the results given in this work. info:eu-repo/semantics/openAccess by http://creativecommons.org/licenses/by/3.0/es/ 2.69 2021 COMPUTER SCIENCE, INFORMATION SYSTEMS 100 / 164 = 0.61 2021 Q3 T2 PHYSICS, APPLIED 82 / 161 = 0.509 2021 Q3 T2 ENGINEERING, ELECTRICAL & ELECTRONIC 139 / 277 = 0.502 2021 Q3 T2 0.59 2021 Computer Networks and Communications 2021 Q2 Signal Processing 2021 Q2 Hardware and Architecture 2021 Q2 Control and Systems Engineering 2021 Q2 3.7 2021 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Zay Pinilla, Ignacio Hernández-López, Carlos Beltrán Blázquez, José Ramón Universidad de Zaragoza (orcid)0000-0002-7500-4650 5008 785 Universidad de Zaragoza Dpto. Ingeniería Electrón.Com. Área Tecnología Electrónica 10, 7 (2021), 810 [16 pp.] Electronics (Basel) Electronics 2079-9292 https://www.mdpi.com/2079-9292/10/7/810 Texto completo de la revista 935545 http://zaguan.unizar.es/record/101575/files/texto_completo.pdf Versión publicada 2861950 http://zaguan.unizar.es/record/101575/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:101575 articulos driver 2023-05-18-14:22:47 ARTICLE