Piano Timbre Development Analysis using Machine Learning

TL;DR

This study uses machine learning to analyze how a concert grand piano's timbre changes after one year of use, revealing spectral flux as a key feature for stage classification and insights into transient chaoticity and note ordering.

Contribution

It demonstrates that spectral flux can perfectly distinguish between new and used piano stages and explores how other psychoacoustic features relate to timbre development.

Findings

Spectral flux clusters piano stages effectively.

SPL, roughness, and fractal dimension order notes by pitch.

Sub-clusters indicate homogenization and chaoticity changes over time.

Abstract

A data set of recorded single played tones of a concert grand piano is investigated using Machine Learning (ML) on psychoacoustic timbre features. The examined instrument has been recorded at two stages: firstly right after manufacture and secondly after being played in a concert hall for one year. A previous study [Plath2019] revealed that listeners clearly distinguished both stages but no clear correlation with acoustics, signal processing tools or verbalizations of perceived differences could be found. Using a Self-Organizing Map (SOM), training single as well as double feature sets, it can be shown that spectral flux is able to perfectly cluster the two stages. Sound Pressure Level (SPL), roughness, and fractal correlation dimension (as a measure for initial transient chaoticity) are furthermore able to order the keys with respect to high and low notes. Combining spectral flux with the three other features in double-feature training sets maintains stage clustering only for SPL and fractal dimension, showing sub-clusters for both stages. These sub-clusters point to a homogenization of SPL for stage 2 with respect to stage 1 and a pronounced ordering and sub-clustering of key regions with respect to initial transient chaoticity.