Spiking Music: Audio Compression with Event Based Auto-encoders
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929231823372288 |
|---|---|
| author | Lisboa, Martim Bellec, Guillaume |
| author_facet | Lisboa, Martim Bellec, Guillaume |
| contents | Neurons in the brain communicate information via punctual events called spikes. The timing of spikes is thought to carry rich information, but it is not clear how to leverage this in digital systems. We demonstrate that event-based encoding is efficient for audio compression. To build this event-based representation we use a deep binary auto-encoder, and under high sparsity pressure, the model enters a regime where the binary event matrix is stored more efficiently with sparse matrix storage algorithms. We test this on the large MAESTRO dataset of piano recordings against vector quantized auto-encoders. Not only does our "Spiking Music compression" algorithm achieve a competitive compression/reconstruction trade-off, but selectivity and synchrony between encoded events and piano key strikes emerge without supervision in the sparse regime. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01571 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Spiking Music: Audio Compression with Event Based Auto-encoders Lisboa, Martim Bellec, Guillaume Sound Machine Learning Neural and Evolutionary Computing Audio and Speech Processing Neurons in the brain communicate information via punctual events called spikes. The timing of spikes is thought to carry rich information, but it is not clear how to leverage this in digital systems. We demonstrate that event-based encoding is efficient for audio compression. To build this event-based representation we use a deep binary auto-encoder, and under high sparsity pressure, the model enters a regime where the binary event matrix is stored more efficiently with sparse matrix storage algorithms. We test this on the large MAESTRO dataset of piano recordings against vector quantized auto-encoders. Not only does our "Spiking Music compression" algorithm achieve a competitive compression/reconstruction trade-off, but selectivity and synchrony between encoded events and piano key strikes emerge without supervision in the sparse regime. |
| title | Spiking Music: Audio Compression with Event Based Auto-encoders |
| topic | Sound Machine Learning Neural and Evolutionary Computing Audio and Speech Processing |
| url | https://arxiv.org/abs/2402.01571 |