tensorflow-speech-recognition icon indicating copy to clipboard operation
tensorflow-speech-recognition copied to clipboard

Published 20 hours ago • verified publisher icon pannous

Getting some ideas from Wavenet?

Open grapemix opened this issue 7 years ago • 4 comments

Since this project is still in planning stage, I guess we are more open for new ideas. The README mentioned the LSTM, but Wavenet yields better results than LSTM accoring to DeepMind's paper. The Wavenet is explained in the following white paper. Do you think it will be too difficult for us to use the Wavenet approach?

https://drive.google.com/file/d/0B3cxcnOkPx9AeWpLVXhkTDJINDQ/view

Thanks.

grapemix avatar Sep 10 '16 01:09 grapemix

Somebody did it already: https://github.com/ibab/tensorflow-wavenet

andrenatal avatar Sep 15 '16 01:09 andrenatal

@andrenatal That implementation doesn't do STT though right? It's an implementation of the generative material stated in the whitepaper I believe.

thomasmurphycodes avatar Sep 26 '16 15:09 thomasmurphycodes

@andrenatal , ty so much. That repo sounds really very interesting. I am not sure if anyone further discuss this direction. Since it is suggestion ticket, I will still leave this ticket open, but if anyone think the discussion is enough, feel free to close this ticket. And thanks all for your time.

grapemix avatar Oct 27 '16 05:10 grapemix

1-d dilated/atrous convolution is the way to go ...

pannous avatar Nov 16 '16 10:11 pannous