A Comparison of Deep Learning Methods for Timbre Analysis in Polyphonic Automatic Music Transcription

Hernández-Oliván, Carlos (Universidad de Zaragoza) ; Zay Pinilla, Ignacio ; Hernández-López, Carlos ; Beltrán Blázquez, José Ramón (Universidad de Zaragoza)

Resumen: 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.

Idioma: Inglés

DOI: 10.3390/electronics10070810

Año: 2021

Publicado en: Electronics 10, 7 (2021), 810 [16 pp.]
ISSN: 2079-9292

Originalmente disponible en: Texto completo de la revista

Factor impacto JCR: 2.69 (2021)

Categ. JCR: COMPUTER SCIENCE, INFORMATION SYSTEMS rank: 100 / 164 = 0.61 (2021) - Q3 - T2
Categ. JCR: PHYSICS, APPLIED rank: 82 / 161 = 0.509 (2021) - Q3 - T2
Categ. JCR: ENGINEERING, ELECTRICAL & ELECTRONIC rank: 139 / 277 = 0.502 (2021) - Q3 - T2

Factor impacto CITESCORE: 3.7 - Computer Science (Q2) - Engineering (Q2)

Factor impacto SCIMAGO: 0.59 - Computer Networks and Communications (Q2) - Signal Processing (Q2) - Hardware and Architecture (Q2) - Control and Systems Engineering (Q2)

Tipo y forma: Artículo (Versión definitiva)

Área (Departamento): Área Tecnología Electrónica (Dpto. Ingeniería Electrón.Com.)