Using Random Codebooks for Audio Neural AutoEncoders - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

Using Random Codebooks for Audio Neural AutoEncoders

Résumé

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.
Fichier principal
Vignette du fichier
EUSIPCO___RANDOM_QUANTIZATION (1).pdf (1004.25 Ko) Télécharger le fichier
bare_jrnl.pdf (998.74 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04705811 , version 1 (24-09-2024)

Identifiants

  • HAL Id : hal-04705811 , version 1

Citer

Benoît Giniès, Xiaoyu Bie, Olivier Fercoq, Gaël Richard. Using Random Codebooks for Audio Neural AutoEncoders. EUROPEAN SIGNAL PROCESSING CONFERENCE 2024 [EUSIPCO], Aug 2024, Lyon, France. ⟨hal-04705811⟩
0 Consultations
0 Téléchargements

Partager

More