Autoencoders for music sound modeling : a comparison of linear, shallow, deep, recurrent and variational models

Fanny Roche Thomas Hueber 1 Samuel Limier Laurent Girin 1
1 GIPSA-CRISSP - CRISSP
GIPSA-DPC - Département Parole et Cognition
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02349406
Contributor : Thomas Hueber <>
Submitted on : Tuesday, November 5, 2019 - 4:20:46 PM
Last modification on : Friday, November 8, 2019 - 11:54:33 AM

Identifiers

  • HAL Id : hal-02349406, version 1

Collections

Citation

Fanny Roche, Thomas Hueber, Samuel Limier, Laurent Girin. Autoencoders for music sound modeling : a comparison of linear, shallow, deep, recurrent and variational models. Sound & Music Computing Conference (SMC), May 2019, Malaga, Spain. ⟨hal-02349406⟩

Share

Metrics

Record views

7