Implementation of Hybrid Deep Reinforcement Learning Technique for Speech Signal Classification

Classification of speech signals is a vital part of speech signal processing systems. With the advent of speech coding and synthesis, the classification of the speech signal is made accurate and faster. Conventional methods are considered inaccurate due to the uncertainty and diversity of speech signals in the case of real speech signal classification. In this paper, we use efficient speech signal classification using a series of neural network classifiers with reinforcement learning operations. Prior classification of speech signals, the study extracts the essential features from the speech signal using Cepstral Analysis. The features are extracted by converting the speech waveform to a parametric representation to obtain a relatively minimized data rate. Hence to improve the precision of classification, Generative Adversarial Networks are used and it tends to classify the speech signal after the extraction of features from the speech signal using the cepstral coefficient. The classifiers are trained with these features initially and the best classifier is chosen to perform the task of classification on new datasets. The validation of testing sets is evaluated using RL that provides feedback to Classifiers. Finally, at the user interface, the signals are played by decoding the signal after being retrieved from the classifier back based on the input query. The results are evaluated in the form of accuracy, recall, precision, f-measure, and error rate, where generative adversarial network attains an increased accuracy rate than other methods: Multi-Layer Perceptron, Recurrent Neural Networks, Deep belief Networks, and Convolutional Neural Networks.     

A dual-band semi-circular patch antenna for WiMAX and WiFi-5/6 applications

A semi-circular patch antenna (SCPA) is designed for WiMAX and WiFi-5/6 communications. The footprint of the proposed SCPA is only 30 × 40 × 1.575 mm³, which is composed of a semi-circular patch and a partial ground plane. The main strength of this work is that the estimated wide dual-frequency span of 2.39–3.75 GHz and 5.39–7.18 GHz are contributed with two sharp resonances at 2.77 and 6.46 GHz, respectively. The proposed SCPA has been practically tested after fabrication. The measured results confirm that the designed antenna achieved the bandwidth necessity for WiMAX 1.5 (2.5–2.69 GHz), WiMAX 2 (3.4–3.6 GHz), WiFi-5 (5.15–5.85 GHz) and WiFi-6 (5.925–7.125 GHz). In the two resonance frequencies of 2.77 and 6.46 GHz, the designed antenna achieved a gain of 2.558 and 4.109 dB, respectively. In addition, the SCPA also manifests good radiation properties and achieves an average efficiency of more than 90%. A professional version of the 3D electromagnetic simulator is utilized to examine the effect of diffident parameters and model the tested antenna.     

Adaptive dewarping of severely warped camera-captured document images based on document map generation

International Journal on Document Analysis and Recognition (IJDAR) - Automated dewarping of camera-captured handwritten documents is a challenging research problem in Computer Vision and Pattern...     

Charge Storage Capabilities of Fractal Porous Silicon Obtained Using Simple Metal Assisted Porosification Method

Silicon - Simpler methods for fabricating electrodes for charge storage applications are required because electrode materials have appreciable significance to enhance the electrochemical...