Apple today previewed software features for cognitive, vision, hearing, and mobility accessibility, along with innovative tools for individuals who are nonspeaking or at risk of losing their ability to speak.| Apple Newsroom
We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called Vall-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. Val...| arXiv.org
Preserve your own voice as synthetic speech: record and capture the essence of your voice to create a digital copy with ‘My-own-voice’ .| Acapela Group
Explore how Microsoft is committed to responsible AI practices and advancing AI technology with ethical principles.| www.microsoft.com
The application of machine learning to accessibility is not new, but as AI explodes in popularity, it’s certainly getting more attention. Auto-craptions| Joe Dolson Web Accessibility
