Multi-Channel Automatic Music Transcription Using Tensor Algebra

TL;DR

This paper introduces a novel approach to automatic music transcription using tensor algebra, aiming to improve the transcription of complex chords by extending existing matrix factorization techniques to multi-channel data.

Contribution

It proposes the use of tensor algebra for multi-channel automatic music transcription, advancing beyond traditional matrix-based methods.

Findings

Tensor-based methods improve transcription accuracy for chords.

Multi-channel approach captures richer musical information.

Enhanced techniques outperform some existing methods.

Abstract

Music is an art, perceived in unique ways by every listener, coming from acoustic signals. In the meantime, standards as musical scores exist to describe it. Even if humans can make this transcription, it is costly in terms of time and efforts, even more with the explosion of information consecutively to the rise of the Internet. In that sense, researches are driven in the direction of Automatic Music Transcription. While this task is considered solved in the case of single notes, it is still open when notes superpose themselves, forming chords. This report aims at developing some of the existing techniques towards Music Transcription, particularly matrix factorization, and introducing the concept of multi-channel automatic music transcription. This concept will be explored with mathematical objects called tensors.