Integration of an RSA-2048-bit public key cryptography solution in the development of secure voice recognition processing applications

The authors initially employs the fast Fourier transform (FFT) approach to transforming voice inputs into digital signals before integrating a speech recognition solution (which includes two models: hidden Markov model (HMM) and artificial neural network (ANN)). To achieve standard-tone identification of digitally store speech, then incorporated 2048-bit Rivest-Shamir-Adleman (RSA) encryption method encrypt decrypt speech. authors’ building team constructed program using 256-bit advanced standard - Galois counter mode (AES-GCM) assure application’s effectiveness. successfully created application according HMM ANN. collected findings suggest that secure (named soft RSA) has improved in terms safety, keeping material secret, speed. It takes roughly 0.2 s generate RSA key pair exceeds National Institute Standards Technology (NIST) standard, 700-1070 ms process 1-4 RSA, 6-8 RSA.