A Photo-realistic Voice-bot
Year: 2019
Type: dissertation
Abstract: Technology is at the point where systems are capable of synthesizing video of human actors indistinguishably from ones in which the actor is present. This research investigates whether or not it is possible to use this technology in order to create a system which, allows video generation of a human actor, that is able to interact with a user through speech in real-time, whilst also remaining indistinguishable from a real human actor. In other words, a photo-realistic voicebot. The work discusses the motivations and ethics, but also presents and tests a prototype system. The prototype aims to take advantage of the latest in real-time video manipulation software to create a natural sounding conversation with an artificially synthesized video.
Author: J. K. Alexander
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Keywords: voicebots, synthetic video, chatbots, prototype system
Open Access status: green
OpenAlex ID: W2980278776
