Spiking Music: Audio Compression with Event Based Auto-encoders

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 …

audio auto brain build clear compression cs.lg cs.ne cs.sd digital eess.as encoding event events information music neurons representation systems thought via