Robust Sound Onset Detection Using Leaky Integrate-and-Fire Neurons With Depressing Synapses

Abstract

A biologically inspired technique for detecting onsets in sound is presented. Outputs from a cochlea-like filter are spike coded, in a way similar to the auditory nerve (AN). These AN-like spikes are presented to a leaky integrate-and-fire neuron through a depressing synapse. Onsets are detected with essentially zero latency relative to these AN spikes. Onset detection results for a tone burst, musical sounds and the DARPA/NIST TIMIT speech corpus are presented.

A neurally inspired musical instrument classification system based upon the sound onset

“…Biologically inspired tone descriptor based on the onset For the Strategy A tone classification system, a neurallike coding of the perceptual sound onset 39,40 was used as the tone descriptor. The onset detection technique was based on a simple model of the mammalian auditory system, illustrated in Fig.…”

“…6 However, its parallel coding makes it suitable for use with a secondary onset detection system. 39,40 This system was inspired by the onset response behavior exhibited by octopus, and some bushy and stellate cells, 10 cells within the cochlear nucleus.…”

Biologically-inspired neural coding of sound onset for a musical sound classification task

“…The cochlea response was modelled with the ubiquitous passive gammatone filterbank (A) [20]. The output from each gammatone filter was spike-encoded (B) using a zero-crossing based technique [31], the design of which was inspired by the phase-locked spiking behaviour observed in neurons which innervate the cochlea's inner hair cells (IHC) [32]. This encoding thus provides a crude simulation of the auditory nerve's (AN) early response to sound stimuli.…”

“…This encoding thus provides a crude simulation of the auditory nerve's (AN) early response to sound stimuli. The strong spiking onset response observed by certain neurons within the cochlear nucleus [14] was then modelled using an array of leaky integrate-and-fire (LIF) neurons, innervated by the simulated AN signal (C), as implemented in [31]. Example outputs from these processing stages are shown in Fig.…”

“…This ensured that multiple ESPSs from adjacent synapses were required for the neuron potential to be large enough to fire. The neurons employed were also leaky [36], [31], meaning that the ESPSs needed to be close to concurrent for an action potential, or 'onset spike', to be produced.…”