A learned audio codec represents 2.98 seconds of audio as 32 sparse events, each decoded as a noise burst convolved with decaying resonances and a room impulse response.
Spiking Music: Audio Compression with Event Based Auto-encoders
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Toward a Sparse and Interpretable Audio Codec
A learned audio codec represents 2.98 seconds of audio as 32 sparse events, each decoded as a noise burst convolved with decaying resonances and a room impulse response.