Guardado en:
| Autor principal: | |
|---|---|
| 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 |