arXiv Open Access 2022

SSM-Net: feature learning for Music Structure Analysis using a Self-Similarity-Matrix based loss

Geoffroy Peeters Florian Angulo

Lihat Sumber

Abstrak

In this paper, we propose a new paradigm to learn audio features for Music Structure Analysis (MSA). We train a deep encoder to learn features such that the Self-Similarity-Matrix (SSM) resulting from those approximates a ground-truth SSM. This is done by minimizing a loss between both SSMs. Since this loss is differentiable w.r.t. its input features we can train the encoder in a straightforward way. We successfully demonstrate the use of this training paradigm using the Area Under the Curve ROC (AUC) on the RWC-Pop dataset.

Topik & Kata Kunci

cs.SD cs.LG eess.AS

Penulis (2)

Geoffroy Peeters

Florian Angulo

Format Sitasi

APA MLA BibTeX

Peeters, G., Angulo, F. (2022). SSM-Net: feature learning for Music Structure Analysis using a Self-Similarity-Matrix based loss. https://arxiv.org/abs/2211.08141

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2022
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓