Search

This paper proposes a real-time sound source localization and tracking architecture based on the abilityof the mammalian auditory system using the interaural intensity difference. We used an innovative bin- aural Neuromorphic Auditory Sensor to obtain spike rates similar to those generated by the inner haircells of the human auditory system. The design of the component that obtains the interaural intensitydifference is inspired by the lateral superior olive. The spike stream that represents the IID is used toturn a robotic platform towards the sound source direction. The architecture was implemented on FPGAdevices using general purpose FPGA resources and was tested with pure tones (1-kHz, 2.5-kHz and 5-kHzsounds) with an average error of 2.32 °. Our architecture demonstrates a potential practical application of sound localization for robots, and can be used to test paradigms for sound localization in the mammalianbrain.

In this paper, we explore the capabilities of a sound classification system that combines a Neuromorphic Auditory System for feature extraction and an artificial neural network for classification. Two models of neural network have been used: Multilayer Perceptron Neural Network and Spiking Neural Network. To compare their accuracies, both networks have been developed and trained to recognize pure tones in presence of white noise. The spiking neural network has been implemented in a FPGA device. The neuromorphic auditory system that is used in this work produces a form of representation that is analogous to the spike outputs of the biological cochlea. Both systems are able to distinguish the different sounds even in the presence of white noise. The recognition system based in a spiking neural networks has better accuracy, above 91 %, even when the sound has white noise with the same power.

In this paper, we explore the capabilities of a sound classification system that combines both a novel FPGA cochlear model implementation and a bio-inspired technique based on a trained convolutional spiking network. The neuromorphic auditory system that is used in this work produces a form of representation that is analogous to the spike outputs of the biological cochlea. The auditory system has been developed using a set of spike-based processing building blocks in the frequency domain. They form a set of band pass filters in the spike-domain that splits the audio information in 128 frequency channels, 64 for each of two audio sources. Address Event Representation (AER) is used to communicate the auditory system with the convolutional spiking network. A layer of convolutional spiking network is developed and trained on a computer with the ability to detect two kinds of sound: artificial pure tones in the presence of white noise and electronic musical notes. After the training process, the presented system is able to distinguish the different sounds in real-time, even in the presence of white noise.