A Model You Can Hear: Audio Identification with Playable Prototypes

Machine learning techniques have proved useful for classifying and analyzing audio content. However, recent methods typically rely on abstract and high-dimensional representations that are difficult to interpret. Inspired by transformation-invariant approaches developed for image and 3D data, we pro...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-08
Main Authors: Loiseau, Romain, Bouvier, Baptiste, Teytaut, Yann, Elliot, Vincent, Aubry, Mathieu, Landrieu, Loic
Format: Article
Language:English
Subjects:
Acoustics
Audio data
Classification
Machine learning
Prototypes
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine learning techniques have proved useful for classifying and analyzing audio content. However, recent methods typically rely on abstract and high-dimensional representations that are difficult to interpret. Inspired by transformation-invariant approaches developed for image and 3D data, we propose an audio identification model based on learnable spectral prototypes. Equipped with dedicated transformation networks, these prototypes can be used to cluster and classify input audio samples from large collections of sounds. Our model can be trained with or without supervision and reaches state-of-the-art results for speaker and instrument identification, while remaining easily interpretable. The code is available at: https://github.com/romainloiseau/a-model-you-can-hear
ISSN:2331-8422