WaveNet: A Generative Model for Raw Audio
deepmind.com
WaveNet: A Generative Model for Raw Audio
1–10 of 153 posts
Re: WaveNet: A Generative Model for Raw Audio
#2Would delete this post if I could. Was a request to fix a broken link. Now fixed.
Re: WaveNet: A Generative Model for Raw Audio
#3Would delete this post if I could. Was a request to fix a broken link. Now fixed.
It seems fixed now.
Re: WaveNet: A Generative Model for Raw Audio
#4Wow. I badly want to try this out with music, but I've taken little more than baby steps with neural networks in the past: am I stuck waiting for someone else to reimplement the stuff in the paper?
IIRC someone published an OSS implementation of the deep dreaming image synthesis paper fairly quickly...
Re: WaveNet: A Generative Model for Raw Audio
#5Do they say how much time is the generation taking?
Is this insanely slow to train but extremely fast to do generation?
Re: WaveNet: A Generative Model for Raw Audio
#6Do they say how much time is the generation taking? Is this insanely slow to train but extremely fast to do generation?
"After training, we can sample the network to generate synthetic utterances. At each step during sampling a value is drawn from the probability distribution computed by the network. This value is then fed back into the input and a new prediction for the next step is made. Building up samples one step at a time like this is computationally expensive, but we have found it essential for generating complex, realistic-sounding audio."
So it looks like generation is a slow process.
Re: WaveNet: A Generative Model for Raw Audio
#7This is incredible. I'd be worried if I were a professional audiobook reader :)
Re: WaveNet: A Generative Model for Raw Audio
#8This is incredible. I'd be worried if I were a professional audiobook reader :)
That is so exciting for me. I love listening to audiobooks when I'm walking my dog, or driving, or something boring that doesn't need my brain but does need my arms.
The issue is the selection is so much smaller than the selection of books.
Re: WaveNet: A Generative Model for Raw Audio
#9The samples sound amazing. These causal convolutions look like a great idea, will have to re-read a few times. All the previous generative audio from raw audio samples I've heard (using LSTM) has been super noisy. These are crystal clear.
Dilated convolutions are already implemented in TF, look forward to someone implementing this paper and publishing the code.
Re: WaveNet: A Generative Model for Raw Audio
#10This is incredible. I'd be worried if I were a professional audiobook reader :)
That is so exciting for me. I love listening to audiobooks when I'm walking my dog, or driving, or something boring that doesn't need my brain but does need my arms. The issue is the selection is so much smaller than the selection of books.
Indeed. It also sounds like it could be trained to correctly read math or code, the two things that require enough expertise to properly pronounce that most text to speech engines fail miserably.
Something like:
a(b+c)
If read with proper inflection, this would be a vast improvement and could open up all sorts of technical material to people for whom audio learning is preferred.
I think back to the first math teacher I had whose pronunciation of the notation was precise and unambiguous enough that one didn't really have to be watching the board. This is a rare gift, yet it is possible in many areas of math, yet few teachers master it (or realize how helpful it is).