The Effect of Perceptual Metrics on Music Representation Learning for Genre Classification

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Namgyal, Tashi, Hepburn, Alexander, Santos-Rodriguez, Raul, Laparra, Valero, Malo, Jesus
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916410993672192
author Namgyal, Tashi
Hepburn, Alexander
Santos-Rodriguez, Raul
Laparra, Valero
Malo, Jesus
author_facet Namgyal, Tashi
Hepburn, Alexander
Santos-Rodriguez, Raul
Laparra, Valero
Malo, Jesus
contents The subjective quality of natural signals can be approximated with objective perceptual metrics. Designed to approximate the perceptual behaviour of human observers, perceptual metrics often reflect structures found in natural signals and neurological pathways. Models trained with perceptual metrics as loss functions can capture perceptually meaningful features from the structures held within these metrics. We demonstrate that using features extracted from autoencoders trained with perceptual losses can improve performance on music understanding tasks, i.e. genre classification, over using these metrics directly as distances when learning a classifier. This result suggests improved generalisation to novel signals when using perceptual metrics as loss functions for representation learning.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17069
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Effect of Perceptual Metrics on Music Representation Learning for Genre Classification
Namgyal, Tashi
Hepburn, Alexander
Santos-Rodriguez, Raul
Laparra, Valero
Malo, Jesus
Sound
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Audio and Speech Processing
The subjective quality of natural signals can be approximated with objective perceptual metrics. Designed to approximate the perceptual behaviour of human observers, perceptual metrics often reflect structures found in natural signals and neurological pathways. Models trained with perceptual metrics as loss functions can capture perceptually meaningful features from the structures held within these metrics. We demonstrate that using features extracted from autoencoders trained with perceptual losses can improve performance on music understanding tasks, i.e. genre classification, over using these metrics directly as distances when learning a classifier. This result suggests improved generalisation to novel signals when using perceptual metrics as loss functions for representation learning.
title The Effect of Perceptual Metrics on Music Representation Learning for Genre Classification
topic Sound
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2409.17069