Evolving a Multi-Classifier System for Multi-Pitch Estimation of Piano Music and Beyond: An Application of Cartesian Genetic Programming

Abstract

This paper presents a new method with a set of desirable properties for multi-pitch estimation of piano recordings. We propose a framework based on a set of classifiers to analyze audio input and to identify piano notes present in a given audio signal. Our system’s classifiers are evolved using Cartesian genetic programming: we take advantage of Cartesian genetic programming to evolve a set of mathematical functions that act as independent classifiers for piano notes. Two significant improvements are described: the use of a harmonic mask for better fitness values and a data augmentation process for improving the training stage. The proposed approach achieves competitive results using F-measure metrics when compared to state-of-the-art algorithms. Then, we go beyond piano and show how it can be directly applied to other musical instruments, achieving even better results. Our system’s architecture is also described to show the feasibility of its parallelization and its implementation as a real-time system. Our methodology is also a white-box optimization approach that allows for clear analysis of the solutions found and for researchers to learn and test improvements based on the new findings.

Music Singing Based on Computer Analog Piano Accompaniment and Digital Processing for 5G Industrial Internet of Things

“…With the arrival of the era of artificial intelligence, digital processing technology to further promote the development of music system to the direction of intelligence, people have a deeper pursuit of music, hope that the computer can "understand" the content of music, and replace professionals to complete music classification, music personality recommendation, music creation and other work [2]. Therefore, the application of artificial intelligence in music singing to assist people to complete music singing is a research direction combining computer technology, signal digital processing, and musicology [3,4]. As the musical signal changes with time, that is, the musical state or feature will change with time, and the state at different moments will have a certain connection.…”

Intelligent Permanent Magnet Motor-Based Servo Drive System Used for Automated Tuning of Piano

“…However, it is well-known that tuning a piano is complicated because there are over two hundred strings to be tuned and professional temperament knowledge is required [2]. Concerning this issue, piano tuning has been studied for over three hundred years, since the birth of the piano, with a variety of tuning techniques developed, which can be divided into three main categories: manual tuning, semi-automated tuning and automated tuning [3][4][5][6].…”

“…When it comes to the automated tuning methods, they become more advanced because the tuning process can be free of manual mechanical operations. Specifically, in comparison with the semi-automated tuning approaches, electronic devices are also needed for sound detection and pitch analysis, but after that, they will generate control signals to actuate a motorized system to turn the pins, tightening or loosening the strings automatically [5,6]. The features of the three tuning techniques are compared in Table 1.…”