Duplex's underlying text-to-speech technology research (WaveNet) has produced se...

		jdietrich on May 20, 2018 \| parent \| context \| favorite \| on: Today’s dominant approach to A.I. has not worked o... Duplex's underlying text-to-speech technology research (WaveNet) has produced several papers and is now in public beta. It represents a huge advance in text-to-speech fidelity, using a remarkably straightforward algorithm. https://arxiv.org/pdf/1609.03499.pdf https://www.isca-speech.org/archive/Interspeech_2017/pdfs/14... https://arxiv.org/pdf/1712.05884.pdf https://cloud.google.com/text-to-speech/

The first paper is almost 2 years old, and text-to-speech seems to be a relatively small component of Duplex.