[Subject Prev][Subject Next][Thread Prev][Thread Next][Date Index][Thread Index]

[hts-users:04556] Re: WaveNet: A Generative Model for Raw Audio


On Thu, Sep 8, 2016 at 12:06 PM Heiga ZEN (Byung Ha CHUN) <heigazen@xxxxxxxxxx> wrote:
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.

Google and DeepMind have launched WaveNet TTS to Google Assistant in US English and Japanese.

https://deepmind.com/blog/wavenet-launches-google-assistant/ 

Heiga

 
Cheers,

Heiga

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