New AI Mimics Any Voice in a Matter of Minutes

In an article written by Shelly Fan for Singularityhub, synthesized speech is artificially created by using “speech DNA”. In an era of fake news, skeptics are concerned about fake audio. Proponents point toward the benefits that could be used by handicapped individuals, such as the blind. The company, Lyrebird, is using a new approach to voice synthesis for AI. Most human-machine audio interfaces use an algorithm to produce sound. It is also easy to distinguish from an actual human due to the robotic staccato. Lyrebird uses something they call Voice DNA. “At its core, Lyrebird is a multi-layer artificial neural network, a type of software that loosely mimics the human brain. Like their biological counterparts, artificial networks “learn” through example, tweaking the connections between each “neuron” until the network generates the correct output. Think of it as tuning a guitar.”  Fake voices could be problematic in a number of ways including for privacy and security issues. RE
Sound Clip Credit: Lyrebird

Read Article Here

Leave a Reply

Your email address will not be published. Required fields are marked *