{"paper":{"title":"Autoencoders for music sound modeling: a comparison of linear, shallow, deep, recurrent and variational models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"2), (2) Arturia, 3) ((1) Univ. Grenoble Alpes, (3) INRIA, CNRS, Fanny Roche (1, France, France), GIPSA-lab, Grenoble, Grenoble INP, Laurent Girin (1, Meylan, Montbonnot, Perception Team, Samuel Limier (2), Thomas Hueber (1)","submitted_at":"2018-06-11T16:39:16Z","abstract_excerpt":"This study investigates the use of non-linear unsupervised dimensionality reduction techniques to compress a music dataset into a low-dimensional representation which can be used in turn for the synthesis of new sounds. We systematically compare (shallow) autoencoders (AEs), deep autoencoders (DAEs), recurrent autoencoders (with Long Short-Term Memory cells -- LSTM-AEs) and variational autoencoders (VAEs) with principal component analysis (PCA) for representing the high-resolution short-term magnitude spectrum of a large and dense dataset of music notes into a lower-dimensional vector (and the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04096","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}