Baidu Deep Voice Explained: Part 1 – the Inference Pipeline

Re:Baidu Deep Voice Explained: Part 1 – the Inference Pipeline by reedlaw on Wednesday March 08, 2017 @04:24AM (#13819079)

Are there any how-to guides to getting something like this running? Or are there missing pieces of closed-source software needed? I'm interested in the theory but it helps to be able to try it out.

[ Parent | on HN ]

Re:Baidu Deep Voice Explained: Part 1 – the Inference Pipeline by kastnerkyle on Wednesday March 08, 2017 @12:37PM (#13821841)

If you want to see the most basic form of this pipeline, I have a blog post on "bad speech synthesis" [0]. There are open source versions of WaveNet for TTS [1], but I have not run the code myself or seen the quality of the output. Our code for char2wav is theoretically available [2], but not yet ready for "how-to-guide" level use.

[0] http://kastnerkyle.github.io/posts/bad-speech-synthesis-made...

[1] https://github.com/buriburisuri/speech-to-text-wavenet

[2] https://github.com/sotelo/parrot

[ Parent | on HN ]

Re:Baidu Deep Voice Explained: Part 1 – the Inference Pipeline by stephengillie on Wednesday March 08, 2017 @05:30AM (#13819327)

Microsoft's speech libraries are easily accessible thru a .NET-clr language, such as C# or Powershell. I made a voice-bot as a weekend project last year: https://news.ycombinator.com/item?id=11663029

[ Parent | on HN ]

Re:Baidu Deep Voice Explained: Part 1 – the Inference Pipeline by ttandon on Wednesday March 08, 2017 @05:02AM (#13819211)

Dhruv's planning on putting out a series of posts, where he'll probably be including the model training/set up components! Look out for the next bits this coming week.

[ Parent | on HN ]