News for hackers. Stuff that matters.
Re:Recurrent Neural Nets for Speech Synthesis by julespitt on Monday January 18, 2016 @02:51PM (#10926457)
Went looking for audio samples, here's some from one of the researchers:

http://www.zhizheng.org/demo/is15_mte/demo.html http://www.zhizheng.org/demo/dnn_tts/demo.html

Re:Recurrent Neural Nets for Speech Synthesis by raverbashing on Monday January 18, 2016 @03:15PM (#10926607)
Re:Recurrent Neural Nets for Speech Synthesis by sawwit on Monday January 18, 2016 @03:46PM (#10926792)
I thought this would be about text-to-speech applications, while this seems more like an encoder-decoder problem (make the network learn a pattern and then let it reproduce it). I'm wondering how long it is until we see working TTS based on LSTM RNNs.
Re:Recurrent Neural Nets for Speech Synthesis by ghayes on Monday January 18, 2016 @04:31PM (#10927117)
Yeah, can someone explain the exact problem of "statistical parametric speech synthesis," since I can't find a general overview of the problem itself.
Re:Recurrent Neural Nets for Speech Synthesis by amelius on Monday January 18, 2016 @05:39PM (#10927538)
I'm a newbie to all this, but I can imagine it could be useful for speech compression.