Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

WaveNet: A Generative Model for Raw Audio

deepmind.com

Post reply on HN
Print view View original

131–140 of 153 posts

Re: WaveNet: A Generative Model for Raw Audio

#131

Post by kuschku »

noonespecial wrote: post #97
kuschku wrote: post #94

Earlier quoted context omitted.

So if I remix just 200 songs together, the result is not copyright protected anymore?

No its not like remixing. Its more like listening to 200 songs and then writing one that sounds just like them. More like turning the songs into series of numbers (say 44100 of these numbers per second) and then using an AI to predict which number comes next to make a song that sounds something like the 200. The result is not possible without ingesting the 200 songs but the 200 songs are not "contained" in the net an…

In the US legal system, that’d still be a derived work.

This might be an interesting read for you: http://ansuz.sooke.bc.ca/entry/23

Re: WaveNet: A Generative Model for Raw Audio

#132

Post by rattray »

vintermann wrote: post #107
novalis78 wrote: post #79

Earlier quoted context omitted.

Indeed. I was surprised by that as well. Sounded like a Dutch speaker with a muffled voice behind a screen.

Especially funny as the main authors are Dutch.

Ah. Perhaps it was trained on Dutch speakers, not English.

Re: WaveNet: A Generative Model for Raw Audio

#133

Post by ycombinatorMan »

spiritus_ wrote: post #119
thomasahle wrote: post #108

Earlier quoted context omitted.

There could be cases where the intonation is dependent on things entirely outside of the book. If say a politician does something in the writing that is far from what we would expect them to do in today's world.

Like traditional audio books can capture perfectly what you're referring to...

They can, though?

Re: WaveNet: A Generative Model for Raw Audio

#134

Post by VikingCoder »

itcrowd wrote: post #62
erichocean wrote: post #14

This can be used to implement seamless voice performance transfer from one speaker to another: 1. Train a WaveNet with the source speaker. 2. Train a second WaveNet with the target speaker. Or for something totally new, train a WaveNet with a bunch of different speakers until you get one you like. This becomes the target WaveNet . 3. Record raw audio from the source speaker. Fun fact: any algorithmic process that "re…

Another fun fact: this actually happens with (cell) phone calls. You don't send your speech over the line, instead you send some parameters over the line which are then, at the receiving end, fed into a white(-ish) noise generator to recover the speech. Edit: not by using a neural net or deep learning, of course.

What's the difference in bandwidth?

Re: WaveNet: A Generative Model for Raw Audio

#135

Post by visarga »

jay-anderson wrote: post #105

Any suggestions on where to start learning how to implement this? I understand some of the high level concepts (and took an intro AI class years ago - probably not terribly useful), but some of them are very much over my head (e.g. 2.2 Softmax Distributions and 2.3 Gated Activation Units) and some parts of the paper feel somewhat hand-wavy (2.6 Context Stacks). Any pointers would be useful as I attempt to understand…

Best advice is to wait for a version to pop up on github. It's hard to implement such a paper as a beginner.

Re: WaveNet: A Generative Model for Raw Audio

#136

Post by visarga »

thomasahle wrote: post #108
Houshalter wrote: post #90

Earlier quoted context omitted.

And who says it can't understand the material? There have been recurrent networks trained that can translate between languages, or predict the next word in a sentence, at remarkable accuracy. Combined with wavenet this could be quite effective.

There could be cases where the intonation is dependent on things entirely outside of the book. If say a politician does something in the writing that is far from what we would expect them to do in today's world.

How about we allow annotation of text with prosody cues? Mark the words you want stressed. We already use question and exclamation marks.

Re: WaveNet: A Generative Model for Raw Audio

#137

Post by visarga »

mdip wrote: post #78
grandalf wrote: post #7

This is incredible. I'd be worried if I were a professional audiobook reader :)

I'm an audiobook junkie and as far as professional narrators go, I think it'd be hard to replace a high-end performance with something computer generated and end up with the level of quality offered by the likes of a great narrator like Scott Brick. I mention him by name because it was him that made me realize how important good quality narration is. I had purchased a book at an airport bookstore on a whim and while…

I only fell in love with the voice of a single audiobook narrator. I checked, and yes, he was Scott Brick. I think he adds about 50% on top of the value of the written book by his interpretation.

Re: WaveNet: A Generative Model for Raw Audio

#138

Post by dontreact »

chestervonwinch wrote: post #126
dontreact wrote: post #88

Earlier quoted context omitted.

There is a link to examples at the end

Interesting! So if I understand correctly, much of the noise in the generated audio is due to the noise in the learned filters? I assume some regularization is added to the weights during training, say L1 or L2? If this is the case, this essentially equivalent to assuming the weight values are distributed i.i.d. Laplacian or Gaussian. It seems you could learn less noisy filters by using a prior that assumes dependenc…

Yes. Working on some different regularization techniques.

Re: WaveNet: A Generative Model for Raw Audio

#139

Post by ArkyBeagle »

augustl wrote: post #106
ArkyBeagle wrote: post #57

Earlier quoted context omitted.

That seems completely tractable by simply adding a bit of the right reverb to the generated sample, more or less "in post".

Good point! Just train it with recordings that has no reverberation, and add it later.

It's quite difficult to have no reverberation, but not too bad at all to keep to a minimum. But reverb plus reverb equals reverb, so it's just a matter of finding one that sounds good.

It'd also be interesting to know if this technique could solve the "de-reverberation" problem.

Re: WaveNet: A Generative Model for Raw Audio

#140

Post by microtherion »

fastoptimizer wrote: post #5

Do they say how much time is the generation taking? Is this insanely slow to train but extremely fast to do generation?

According to 3rd hand reports I've heard (apply copious amounts of salt), it may take 1 hour of CPU time to generate 1 second of speech.
Post reply on HN