Microsoft has built a new AI-based speech generator that can mimic how you talk after hearing it for just 3 seconds
A newly developed text-to-speech language model from Microsoft can mimic a person’s speech from as little as three seconds of sample audio – but the tech giant is keeping its tech under wraps for now so it is not misused. One of Microsoft’s artificial intelligence (AI) research teams published a paper about its model for text-to-speech… Read more »