Google Deep Dream
Google Deep Dream
Out of context: Reply #71
- Started
- Last post
- 73 Responses
- drgs2
https://deepmind.com/blog/wavene…
"If we train the network without the text sequence, it still generates speech, but now it has to make up what to say. As you can hear from the samples below, this results in a kind of babbling, where real words are interspersed with made-up word-like sounds.
Notice that non-speech sounds, such as breathing and mouth movements, are also sometimes generated by WaveNet; this reflects the greater flexibility of a raw-audio model."
https://storage.googleapis.com/d…
https://storage.googleapis.com/d…
https://storage.googleapis.com/d…
https://storage.googleapis.com/d…
https://storage.googleapis.com/d…
https://storage.googleapis.com/d…english - any sense = dutch
- Beautiful! I love the last one's irish intonation. The future is going to be such a weird place.detritus
- https://twitter.com/…
90 minutes to synthesize 1 sec of audio, it will take 5-10 years before we can have it on our laptopsdrgs - As dumb a shit as I am, that makes me feel a pico-futile smarter.detritus