Proceedings of the 10th Convention of the
European Acoustics Association
Forum Acusticum 2023


Politecnico di Torino
Torino, Italy
September 11 - 15, 2023





Session: A11-03: Perception and Behaviour in Complex Acoustic Scenes - Part I
Date: Wednesday 13 September 2023
Time: 14:00 - 14:20
Title: Musical timbre classification using FFT-Acoustic Descriptors and Machine Learning
Author(s): Y. Gonzalez, Federal University of ABC (UFABC), Av. Dos Estados 5001, Santo André SP, Brazil, 09210-580 Santo André, Brazil
R.C. Prati, Federal University of ABC (UFABC), Av. Dos Estados 5001, Santo André SP, Brazil, 09210-580 Santo André, Brazil
Pages: 3345-3351
DOI: https://www.doi.org/10.61782/fa.2023.0501
PDF: https://dael.euracoustics.org/confs/fa2023/data/articles/000501.pdf
Conference proceedings
Abstract

Musical timbre is a complex multidimensional attribute of auditory perception, which allows, in a first approximation, to discriminate between musical instruments when they have the same sound, intensity, and duration. One of the challenges in discriminating musical timbres is that, in some cases, there are sounds that appear to have very close timbral similarity, even when the instruments have different acoustic characteristics. This fact can make it difficult to classify musical instruments by timbres. In the present study, we explore a 7-dimensional abstract space, formed by the fundamental frequency and acoustic descriptors extracted from Fourier Transform in five musical instruments: Trumpet, violin, cello, transverse flute, and clarinet, of a monophonic audio record, from the Tinysol and Good-Sounds databases, corresponding to the fourth octave. This approach makes it possible to define a collection of points in timbral space uniquely and allows differentiating sounds played in ordinary style on any type of musical instrument. Through the geometric distance between musical sounds, we explore some Machine Learning techniques to establish categories of similarities between musical sounds, instruments, and dynamics. It is concluded that the study of timbral similarity through geometric distances made it possible to find clustering between categories of musical timbre.