Guardado en:
Detalles Bibliográficos
Autor principal: Vinyard, John
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.05654
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915279061123072
author Vinyard, John
author_facet Vinyard, John
contents Most widely-used modern audio codecs, such as Ogg Vorbis and MP3, as well as more recent "neural" codecs like Meta's Encodec or the Descript Audio Codec are based on block-coding; audio is divided into overlapping, fixed-size "frames" which are then compressed. While they often yield excellent reproductions and can be used for downstream tasks such as text-to-audio, they do not produce an intuitive, directly-interpretable representation. In this work, we introduce a proof-of-concept audio encoder that represents audio as a sparse set of events and their times-of-occurrence. Rudimentary physics-based assumptions are used to model attack and the physical resonance of both the instrument being played and the room in which a performance occurs, hopefully encouraging a sparse, parsimonious, and easy-to-interpret representation.
format Preprint
id arxiv_https___arxiv_org_abs_2505_05654
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Toward a Sparse and Interpretable Audio Codec
Vinyard, John
Sound
Audio and Speech Processing
Most widely-used modern audio codecs, such as Ogg Vorbis and MP3, as well as more recent "neural" codecs like Meta's Encodec or the Descript Audio Codec are based on block-coding; audio is divided into overlapping, fixed-size "frames" which are then compressed. While they often yield excellent reproductions and can be used for downstream tasks such as text-to-audio, they do not produce an intuitive, directly-interpretable representation. In this work, we introduce a proof-of-concept audio encoder that represents audio as a sparse set of events and their times-of-occurrence. Rudimentary physics-based assumptions are used to model attack and the physical resonance of both the instrument being played and the room in which a performance occurs, hopefully encouraging a sparse, parsimonious, and easy-to-interpret representation.
title Toward a Sparse and Interpretable Audio Codec
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2505.05654