Resumen de AI hears snippets of you, then clones your voice
Researchers at China's search engine giant Baidu suggest that neural networks technology could create digital duplicate voices for people who have lost the ability to talk. The company's research builds on its text-to-speech synthesis system Deep Voice, which was trained on more than 800 hours of audio from 2,400 speakers. The technology could also be used to personalise digital assistants, video game characters or automatic speech translation services
