Using Random Codebooks for Audio Neural AutoEncoders

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Giniès, Benoît, Bie, Xiaoyu, Fercoq, Olivier, Richard, Gaël
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914956921798656
author Giniès, Benoît
Bie, Xiaoyu
Fercoq, Olivier
Richard, Gaël
author_facet Giniès, Benoît
Bie, Xiaoyu
Fercoq, Olivier
Richard, Gaël
contents Latent representation learning has been an active field of study for decades in numerous applications. Inspired among others by the tokenization from Natural Language Processing and motivated by the research of a simple data representation, recent works have introduced a quantization step into the feature extraction. In this work, we propose a novel strategy to build the neural discrete representation by means of random codebooks. These codebooks are obtained by randomly sampling a large, predefined fixed codebook. We experimentally show the merits and potential of our approach in a task of audio compression and reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2409_16677
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Using Random Codebooks for Audio Neural AutoEncoders
Giniès, Benoît
Bie, Xiaoyu
Fercoq, Olivier
Richard, Gaël
Signal Processing
Latent representation learning has been an active field of study for decades in numerous applications. Inspired among others by the tokenization from Natural Language Processing and motivated by the research of a simple data representation, recent works have introduced a quantization step into the feature extraction. In this work, we propose a novel strategy to build the neural discrete representation by means of random codebooks. These codebooks are obtained by randomly sampling a large, predefined fixed codebook. We experimentally show the merits and potential of our approach in a task of audio compression and reconstruction.
title Using Random Codebooks for Audio Neural AutoEncoders
topic Signal Processing
url https://arxiv.org/abs/2409.16677