A Complete Hardware Implementation of an Integrated Sound Localization and Classification System Based on Spiking Neural Networks

Kugler, Mauricio; Iwasa, Kaname; Benso, Victor Alberto; Kuroyanagi, Sachiko; Iwata, Atsushi

doi:10.1007/978-3-540-69162-4_60

Cited by 7 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the 500 Hz to 8 kHz frequency range shows smaller standard deviation than the 40 Hz to 8 kHz frequency range at −90 • when the diagonal correlogram is used, which indicates our simplest hardware implementation is sufficient for this task. Table 4 shows comparisons of the proposed system with other biologically inspired sound localisation systems [26,63,64]. Human sound localisation performance reported in Reference [65] is also included in the table.…”

Section: Results and Comparisonsmentioning

confidence: 99%

“…To emulate the robustness of the human sound localisation performance in noisy environments, neural network algorithms are introduced to analyse the ITD cues from cochlear models. Implementations of such auditory "where" pathways have been proposed and developed increasingly [23][24][25][26][27]. For example, K. Iwasa et al [25] and M. Kugler et al [26] used a competitive learning network with a pulsed neuron model (CONP) to learn the direction of a sound source.…”

Section: Introductionmentioning

confidence: 99%

“…Implementations of such auditory "where" pathways have been proposed and developed increasingly [23][24][25][26][27]. For example, K. Iwasa et al [25] and M. Kugler et al [26] used a competitive learning network with a pulsed neuron model (CONP) to learn the direction of a sound source. C. Schauer et al [28] proposed to build a spikebased sound localisation system on Field Programmable Gate Array (FPGA).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Biologically Inspired Sound Localisation System Using a Silicon Cochlea Pair

Afshar

Wang

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

We present a biologically inspired sound localisation system for reverberant environments using the Cascade of Asymmetric Resonators with Fast-Acting Compression (CAR-FAC) cochlear model. The system exploits a CAR-FAC pair to pre-process binaural signals that travel through the inherent delay line of the cascade structures, as each filter acts as a delay unit. Following the filtering, each cochlear channel is cross-correlated with all the channels of the other cochlea using a quantised instantaneous correlation function to form a 2-D instantaneous correlation matrix (correlogram). The correlogram contains both interaural time difference and spectral information. The generated correlograms are analysed using a regression neural network for localisation. We investigate the effect of the CAR-FAC nonlinearity on the system performance by comparing it with a CAR only version. To verify that the CAR/CAR-FAC and the quantised instantaneous correlation provide a suitable basis with which to perform sound localisation tasks, a linear regression, an extreme learning machine, and a convolutional neural network are trained to learn the azimuthal angle of the sound source from the correlogram. The system is evaluated using speech data recorded in a reverberant environment. We compare the performance of the linear CAR and nonlinear CAR-FAC models with current sound localisation systems as well as with human performance.

show abstract