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

WaveNet launches in the Google Assistant

deepmind.com

Post reply on HN
Print view View original

51–60 of 122 posts

Re: WaveNet launches in the Google Assistant

#51

Post by thorum »

degenerate wrote: post #36
exhilaration wrote: post #19

Earlier quoted context omitted.

One of my co-workers told me in 2012 that he was doing exactly this. He used an ebook reader to download free ebooks from Gutenberg and then the IVONA text to speech engine for Android to listen to them on his drives. He had already finished a few classics like Treasure Island this way. I'm sure things have improved significantly since 2012 so what you're looking for is probably easily done.

If your co-worker could share how he did this, it would be appreciated (specifically, what apps/code needs to be run).

Not the coworker, but I've been doing this for a couple years. If you're on iOS, the simplest option is Voice Dream Reader [1].

It can read .epub files directly, along with text files and webpages, and integrates with Dropbox, Pocket, Gutenberg, etc.

On Android, you can get Voice Dream Reader (though it has less features than on iOS) or @Voice Aloud Reader which is free [2].

[1] http://www.voicedream.com/reader/

[2] http://www.hyperionics.com/atVoice/

Re: WaveNet launches in the Google Assistant

#52

Post by nicklovescode »

DanAndersen wrote: post #18

I'm most interested in its potential for audiobooks, especially of the vast array of old and less-common books that don't have human-made audiobook equivalents. I find myself constrained by the limits of audiobook choices, which tends toward best-sellers lists or pop-sci. Current attempts to use text-to-speech to generate audiobooks results in something that's frankly unlistenable. If TTS could get to a "good enough"…

I don't have time at the moment to search it out, but in a previous speech-synth thread there's an in depth discussion of this. In short, people were pessimistic on wavenet as audiobook because audiobooks are all about knowing the story and speaking accordingly

Re: WaveNet launches in the Google Assistant

#53

Post by alexasmyths »

These things are highly nuanced.

The amount of tweaking and finessing that goes on under the hood for specific scenarios can change outcomes quite a lot.

And from a product perspective, it can be taken quite far - for example, most of the 'common' things Siri says are not synthesized, it's literally are recording of the voice over artists. The more arcane stuff is synthesized.

It's always comparing apples to oranges to bananas unless you really know what they're doing, even then it's hard.

Re: WaveNet launches in the Google Assistant

#54

Post by kuschku »

wmf wrote: post #49
kuschku wrote: post #48

Earlier quoted context omitted.

I sure hope so, although I am extremely angered that they don’t release the model. Google is only having any success with this because they are getting training data from the public for free, they should also return the model to the public for free (at least for noncommercial use)

And their Web ranking model and their spam filtering model? Face it, Google's gonna be Google. (And I don't think WaveNet is even based on public training data.)

Well, we have to have some ideals, so we can work towards them.

Public Money, Public Code should also extend to Public Data, Public Code.

Re: WaveNet launches in the Google Assistant

#56

Post by spuz »

Yhippa wrote: post #24
sgk284 wrote: post #6

Earlier quoted context omitted.

If you ever listen to people try to record sound that's clear and precise, they actually sound fairly robotic. See this Google 20% Project where they explore Google Assistant's voice creation: https://youtu.be/qnGNfz7JiZ8?t=5m23s WaveNet is probably modeling the source data very well. It sounds like they just need more data with emotion and inflection, rather than having source data that is optimized for monotonicity…

The improved voices sound exactly like the audio from CBT's I've taken in the past. Could possibly have fooled me.

What is CBT?

Re: WaveNet launches in the Google Assistant

#57

Post by StavrosK »

I would love something like this for computer notifications, or any sort of automated system notification. For a concrete example, my RC controller has the ability to do voice prompts (e.g. "landing gear down"), and it would be great if I could get a high-quality voice to speak all this.

Hell, I'd settle for an API where I could send text and get high-quality voice back. Maybe I can somehow hack the Google Assistant app to do it...

Re: WaveNet launches in the Google Assistant

#58

Post by spuz »

chmod775 wrote: post #31
wmf wrote: post #28

Earlier quoted context omitted.

Does TTS run on the phone or the cloud?

It runs on the phone afaik, while speech recognition on the other hand is supported by stuff Google runs in the cloud. Edit: I might be wrong, at the end of a paragraph they say it runs on Google’s TPU cloud infrastructure, though it isn't clear to me whether they just use that for training. Edit 2: I just tried it on my phone. At least stuff like asking it to "Turn on WiFi" works without an internet connection, and…

> I just tried it on my phone. At least stuff like asking it to "Turn on WiFi" works without an internet connection, and yields a TTS response.

But this is the status quo. You would not expect Google to disable offline TTS just for slightly improved quality. The real question is, is it running Wavenet offline or the previous version of its TTS engine offline?

Re: WaveNet launches in the Google Assistant

#59

Post by spuz »

Tade0 wrote: post #10

I hope somebody uses this to immortalize Sir David Attenborough or the sadly departed Don LaFontaine.

Oh man, I can already see the court cases of a certain robot's voice sounding a little too similar to a deceased human's that it should make royalty payments.

Re: WaveNet launches in the Google Assistant

#60

Post by exhilaration »

degenerate wrote: post #36
exhilaration wrote: post #19

Earlier quoted context omitted.

One of my co-workers told me in 2012 that he was doing exactly this. He used an ebook reader to download free ebooks from Gutenberg and then the IVONA text to speech engine for Android to listen to them on his drives. He had already finished a few classics like Treasure Island this way. I'm sure things have improved significantly since 2012 so what you're looking for is probably easily done.

If your co-worker could share how he did this, it would be appreciated (specifically, what apps/code needs to be run).

For Android take a look at this: https://www.youtube.com/watch?v=MAHg31ucDhY
Post reply on HN