000101575 001__ 101575
000101575 005__ 20230519145435.0
000101575 0247_ $$2doi$$a10.3390/electronics10070810
000101575 0248_ $$2sideral$$a123846
000101575 037__ $$aART-2021-123846
000101575 041__ $$aeng
000101575 100__ $$0(orcid)0000-0002-0235-2267$$aHernández-Oliván, Carlos$$uUniversidad de Zaragoza
000101575 245__ $$aA Comparison of Deep Learning Methods for Timbre Analysis in Polyphonic Automatic Music Transcription
000101575 260__ $$c2021
000101575 5060_ $$aAccess copy available to the general public$$fUnrestricted
000101575 5203_ $$aAutomatic 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.
000101575 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000101575 590__ $$a2.69$$b2021
000101575 592__ $$a0.59$$b2021
000101575 594__ $$a3.7$$b2021
000101575 591__ $$aCOMPUTER SCIENCE, INFORMATION SYSTEMS$$b100 / 164 = 0.61$$c2021$$dQ3$$eT2
000101575 593__ $$aComputer Networks and Communications$$c2021$$dQ2
000101575 591__ $$aPHYSICS, APPLIED$$b82 / 161 = 0.509$$c2021$$dQ3$$eT2
000101575 593__ $$aSignal Processing$$c2021$$dQ2
000101575 591__ $$aENGINEERING, ELECTRICAL & ELECTRONIC$$b139 / 277 = 0.502$$c2021$$dQ3$$eT2
000101575 593__ $$aHardware and Architecture$$c2021$$dQ2
000101575 593__ $$aControl and Systems Engineering$$c2021$$dQ2
000101575 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000101575 700__ $$aZay Pinilla, Ignacio
000101575 700__ $$aHernández-López, Carlos
000101575 700__ $$0(orcid)0000-0002-7500-4650$$aBeltrán Blázquez, José Ramón$$uUniversidad de Zaragoza
000101575 7102_ $$15008$$2785$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Tecnología Electrónica
000101575 773__ $$g10, 7 (2021), 810 [16 pp.]$$pElectronics (Basel)$$tElectronics$$x2079-9292
000101575 85641 $$uhttps://www.mdpi.com/2079-9292/10/7/810$$zTexto completo de la revista
000101575 8564_ $$s935545$$uhttps://zaguan.unizar.es/record/101575/files/texto_completo.pdf$$yVersión publicada
000101575 8564_ $$s2861950$$uhttps://zaguan.unizar.es/record/101575/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000101575 909CO $$ooai:zaguan.unizar.es:101575$$particulos$$pdriver
000101575 951__ $$a2023-05-18-14:22:47
000101575 980__ $$aARTICLE