Artificial Generation of Realistic Voices

Abstract

In this paper, we propose an end-to-end text-to-speech system deployment wherein a user feeds input text data which gets synthesized, variated, and altered into artificial voice at the output end. To create a text-to-speech model, that is, a model capable of generating speech with the help of trained datasets. It follows a process which organizes the entire function to present the output sequence in three parts. These three parts are Speaker Encoder, Synthesizer, and Vocoder. Subsequently, using datasets, the model accomplishes generation of voice with prior training and maintains the naturalness of speech throughout. For naturalness of speech we implement a zero-shot adaption technique. The primary capability of the model is to provide the ability of regeneration of voice, which has a variety of applications in the advancement of the domain of speech synthesis. With the help of speaker encoder, our model synthesizes user generated voice if the user wants the output trained on his/her voice which is feeded through the mic, present in GUI. Regeneration capabilities lie within the domain Voice Regeneration which generates similar voice waveforms for any text.