Making A Computerized Voice A Little More Human

Making A Computerized Voice A Little More Human
March 08, 2014
http://www.npr.org/2014/03/08/287673282/making-a-computerized-voice-a-little-more-human

Speech scientist Rupal Patel customizes synthetic voices for people who can’t speak. She tells TED Radio Hour about helping people communicate in a voice that fits their personality.

You may recognize this as the voice of Stephen Hawking, the physicist. It’s actually the generic voice of men and women who use computers to speak for them. Synthetic speech though can be cold and impersonal, …

original talk:
Rupal Patel: Synthetic voices, as unique as fingerprints
http://www.ted.com/talks/rupal_patel_synthetic_voices_as_unique_as_fingerprints
Dec. 2013

Speech Recognition Breakthrough for the Spoken, Translated Word

Speech Recognition Breakthrough for the Spoken, Translated Word
Microsoft Research
Nov. 8, 2012

Chief Research Officer Rick Rashid demonstrates a speech recognition breakthrough via machine translation that converts his spoken English words into computer-generated Chinese language.
The breakthrough is patterned after deep neural networks and significantly reduces errors in spoken as well as written translation.