I n this paper we report on the application of RNN in an opeti-set text-dependent speaker identification task. MFCC feafirres fiom the speech utterance are fed to 11 neuralnehvork-based classifier to idenfib the speakers. We use a feed-for-u,ard net architecture as proposed by Robinson 111. We introduce a fully connected hidden layer between the input and state nodes and the output. We show that this hidden layer rnakrv the learning of comp1e.x classrfication tasks more efficient. Training uses back propagation through lime. There is one output urd per speuker, with the training forgets corresponding to speaker identity. For I0 male speakers we obtain a true acceptance rate 100% with a .fnlse acceptance rate 10%. For 14 speakers these figures are 94% and 12% respectively We also investigate the eflect qf environmental factors on the identification occiiracy (signal level, change of microphone). choice of ricor,.sric vcctor.s (FFT or MFCC), size of the training ~latahare, inclrision of fundameiital frequency. MFCC fearuws plio fan~~iiIrn,entri/fi.eqlrprlCy give the best results.
Spiking Neural Networks (SNNs) help achieve brain-like efficiency and functionality by building neurons and synapses that mimic the human brain’s transmission of electrical signals. However, optimal SNN implementation requires a precise balance of parametric values. To design such ubiquitous neural networks, a graphical tool for visualizing, analyzing, and explaining the internal behavior of spikes is crucial. Although some popular SNN simulators are available, these tools do not allow users to interact with the neural network during simulation. To this end, we have introduced the first runtime interactive simulator, called Runtime Analyzing and Visualization Simulator (RAVSim), a developed to analyze and dynamically visualize the behavior of SNNs, allowing end-users to interact, observe output concentration reactions, and make changes directly during the simulation. In this paper, we present RAVSim with the current implementation of runtime interaction using the LIF neural model with different connectivity schemes, an image classification model using SNNs, and a dataset creation feature. Our main objective is to primarily investigate binary classification using SNNs with RGB images. We created a feed-forward network using the LIF neural model for an image classification algorithm and evaluated it by using RAVSim. The algorithm classifies faces with and without masks, achieving an accuracy of 91.8% using 1000 neurons in a hidden layer, 0.0758 MSE, and an execution time of ∼10[Formula: see text]min on the CPU. The experimental results show that using RAVSim not only increases network design speed but also accelerates user learning capability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.