Speaker identification and verification over short distance telephone lines using artificial neural networks

Please use artificial neural network for Ganesh K Venayagamoorthy, Narend Sunderpersadh and Theophilus N Andrew for identification and verification of short distance telephone lines. theo@wpo.mlsultan.ac.za ML Sultan Technikon, PO Box 1334, Durban, South Africa. Because of white-collar crime, fraud and corruption, innumerable funds are lost every year. In this article, we will explain a method to combat white collar crime in telephone transactions using artificial neural network (ANN) to identify and verify speakers.

Speaker recognition is the concept of identifying the person to whom the spoken word belongs. Typically, the computer performs these operations by an artificial neural network (ANN), where the trained input network is used to classify the next input audio frame into one of the existing categories . Output categories are usually personal identification information. In audio signal processing, the computer can listen to the sound on a frame-by-frame basis, making "frame" an important element of audio processing. Each frame is the source of much information about the sounds heard by the computer. Typically, an audio frame is a vector of approximately 1000 samples, where a speech segment processed at one time may have a length of a few seconds with hundreds of frames. Let's take an audio frame and calculate its discrete Fourier transform (DFT). Now the frequency amplitude signal is obtained. This is actually a DFT of a specific audio frame.

Application of artificial neural network is called neural computing. Neural computing uses a limited number of concepts borrowed from the biological nervous system. The main purpose of the artificial neural network is to simulate the massively parallel process related to interconnected processing elements within the network architecture. Artificial neurons will form the foundation of artificial neural networks. Neurons receive input from other neurons connected to it. On the other hand, neuron output is passed to several other connected neurons. The same mechanism also occurs in the human brain. You can also change the artificial signal processed by the neuron. How an artificial neural network processes information depends entirely on its structure. The algorithm used to process the information also affects

Let's begin by discussing the neural network. Neural network is an artificial intelligence method based on the human brain. We know that the human brain consists of billions of interconnected neurons. The neural network trains a large amount of data and each layer of the neuron develops a task to perform input from input to input to input. These types of neural networks are the foundation of many of the greatest advances in AI in the past few years, from new outcomes in accurate medical diagnosis to victories in Google and AlphaGo.