Bøger af Virender Kadyan

This book provides insights into deep learning techniques that impact the implementation strategies toward achieving the Sustainable Development Goals (SDGs) laid down by the United Nations for its 2030 agenda, elaborating on the promises, limits, and the new challenges. It also covers the challenges, hurdles, and opportunities in various applications of deep learning for the SDGs. A comprehensive survey on the major applications and research, based on deep learning techniques focused on SDGs through speech and image processing, IoT, security, AR-VR, formal methods, and blockchain, is a feature of this book. In particular, there is a need to extend research into deep learning and its broader application to many sectors and to assess its impact on achieving the SDGs. The chapters in this book help in finding the use of deep learning across all sections of SDGs. The rapid development of deep learning needs to be supported by the organizational insight and oversight necessary for AI-based technologies in general; hence, this book presents and discusses the implications of how deep learning enables the delivery agenda for sustainable development.

In modern speech recognition systems, there are a set of Feature Extraction Techniques (FET) like Mel-frequency cepstral coefficients (MFCC) or perceptual linear prediction coefficients (PLP) are mainly used. As compared to the conventional FET like LPCC etc, these approaches are provide a better speech signal that contains the relevant information of the speech signal uttered by the speaker during training and testing of the Speech To Text Detection System (STTDS) for different Indian languages. In this dissertation, variation in the parameters values of FET¿s like MFCC, PLP are varied at the front end along with dynamic HMM topology at the back end and then the speech signals produce by these techniques are analyzed using HTK toolkit. The cornerstone of all the current state-of-the-art STTDS is the use of HMM acoustic models. In our work the effectiveness of proposed FET(MFCC, PLP features) are tested and the comparison is done among the FET like MFCC and PLP acoustic features to extract the relevant information about what is being spoken from the audio signal and experimental results are computed with varying HMM topology at the back end.