voice creation; voice detection; deep learning; python
Abstract
Advantage of deep learning is very vast in these days. Training of images, videos, audio and test it according to requirement has become simple and user friendly. Still there are some disadvantages and risks. In this paper, we will discuss about audio that created by deep fakes it is very popular word in latest technology fake audio not only terrifying but actually beginning to happen. Fake audio can be used for malicious purposes which affect directly or indirectly human life. For an example, google map use deep learning based navigation; if it modifies then we will be misdirected. In this work, many papers on how to differentiate real or fake audio has been referred. Python and deep learning has been used and implemented to achieve the aim. Audio files or video file are being used as an input of this work then model has been trained for uniquely identify features for voice creation and voice detection. Deep learning technique is used to find accuracy between real and fake.
