Quantum Computing Approach Baby Cry Analysis Using Deep Neural Networks and Convolution Neural Networks

This research presents a inclusive study into the growth of a deep education model handling Convolutional Neural Networks (CNN) for the purpose of discriminating differing causes behind baby crying. The study includes the accumulation and study of baby cry visual and audio entertainment transmitted via radio waves samples, including an far-reaching array of visual and audio entertainment transmitted via radio waves limits in the way that Short-Time Fourier Transform (STFT) Mean, Root Mean Square (RMS) Mean, Spectral Centroid (SC) Mean, Spectral Bandwidth (SBAN) Mean, Zero-Crossing Rate (ZCR) Mean, Mel-repetitiveness Cepstral Coefficients (MFCCs) including MFCCs1 to MFCCs13, alongside accumulation of solid and opening-delta MFCCs13. These diverse visual and audio entertainment transmitted via radio waves appearance are working to train the CNN construction, permissive the model to correctly categorize baby cries established different creative determinants.