Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Faux Rogan. Parent comment
Generative-adversarial models have had a lot of success in image generation; however, the same cannot be said for speech synthesis.
Unless they have figured out a new technique, they are probably using Tacotron 2 (https://ai.googleblog.com/2017/12/tacotron-2-generating-huma...). Google's Tacotron 2 already achieved human-parity TTS without adversarial training as measured by MOS.
There are no comments on this comment yet.
Generative-adversarial models have had a lot of success in image generation; however, the same cannot be said for speech synthesis.
Unless they have figured out a new technique, they are probably using Tacotron 2 (https://ai.googleblog.com/2017/12/tacotron-2-generating-huma...). Google's Tacotron 2 already achieved human-parity TTS without adversarial training as measured by MOS.