[hts-users:04419] WaveNet: A Generative Model for Raw Audio

["Heiga ZEN (Byung Ha CHUN)" <heigazen@xxxxxxxxxx>]

Hi all,

DeepMind researchers and I developed a new generative model for audio signals named "WaveNet".  We can draw a waveform sample-by-sample from this model.  By conditioning linguistic features derived from a text, it can be used for text-to-speech.  It has already overtaken the existing concatenative and parametric TTS significantly.  You can find the result, speech samples, and paper at DeepMind's blog post.

https://deepmind.com/blog/wavenet-generative-model-raw-audio/ 

I believe that this is a milestone in statistical parametric speech synthesis :-)

I'm looking forward to hearing your feedbacks.

Cheers,

Heiga

--

---------------------------------------

Heiga ZEN (in Japanese)
Byung Ha CHUN (in Korean)
<heigazen@xxxxxxxxxx>