Analysis and Optimization of Neural Networks for Image and Speech Recognition

• Published in: 2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES) pp. 1 - 6
• Main Authors: R, Komala C, Purushothaman, R., Ande, Pavan Kumar, Dinesh, P M, S, Anitha Rani K, P, Yamuna
• Format: Conference Proceeding
• Language: English
• Published: IEEE 14-12-2023
• Subjects: Convolution; Fluctuations; Geography; Instruments; Networks; Neural; Optimization; Organizations; Speech recognition; Telephone sets
• DOI: 10.1109/ICSES60034.2023.10465332

The strategy of transforming vocal discourse signals into text using records is known as programmed discourse acknowledgment (ASR). In the ongoing time of the PC unrest, the ASR has a huge impact in further developing the client experience while communicating with the PCs in a characteristic manner. Conventional instruments like a console and mouse can't be utilized, and the client might do a limitless number of undertakings like controlling of contraptions and correspondence with client care. This study presents an air terminal enquiry framework in view of ASR. The program was made solely for the Telugu language. In view of the most generally posed inquiries about air terminals, a data set was created. Convolutional Brain Organization (CNN) has been utilized for preparing and testing the information base in view of its extraordinary exhibition. Convolution brain organizations (CNNs) have as of late been demonstrated to perform better on the telephone discovery test than regular completely associated profound brain networks when utilized in a half and half profound brain organization/stowed away Markov model (DNN/Gee) design.