WaveNet launches in the Google Assistant

Re:WaveNet launches in the Google Assistant by DanAndersen on Wednesday October 04, 2017 @03:56PM (#15403962)

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" point for audiobooks, that would open up a huge range of less-common content.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by dingle_thunk on Wednesday October 04, 2017 @10:26PM (#15406354)

I've used "Voice Dream" for this for years. It's brilliant. iOS/Android text to speech app:

http://www.voicedream.com/reader/

It has so many voices available in the voice store, and I've had no trouble reading books with it. I'm constantly amazed by the quality of some of these voices when played at high speed... They take breaths, express emotion, everything. My only problem is they occasionally mispronounce brands, names & acronyms: Quite amusing to learn about "Sharr-E-poynt" instead of "SharePoint", "Amd" not "A.M.D", or use an incorrect pronunciation of a character in a book when talking about the book... Can't really see how WaveNet would fix that, but look forward to seeing these voices turn up in Voice Dream.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by mavhc on Thursday October 05, 2017 @04:27AM (#15407488)

Tried the 3 demos they linked to, the new Google one is so much better, let's hope they follow suite and improve

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by Immortalin on Wednesday October 04, 2017 @09:31PM (#15406179)

Shameless Plug: https://auditus.cc

Uses Amazon Polly for the speech gen

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by DanAndersen on Thursday October 05, 2017 @08:24AM (#15408540)

Neat! I'll have to look into this.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by exhilaration on Wednesday October 04, 2017 @04:01PM (#15404013)

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.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by degenerate on Wednesday October 04, 2017 @04:35PM (#15404362)

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

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by thorum on Wednesday October 04, 2017 @05:17PM (#15404782)

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/

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by woodson on Wednesday October 04, 2017 @07:38PM (#15405720)

It also works reasonably well for academic papers as PDF. Equations get butchered, of course, but overall it's not bad (you can set PDF margins so that headers/footers are not read out aloud on every page). I use it to proof-read my own writing, it helps you spot things that spelling/grammer checkers miss.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by sangnoir on Wednesday October 04, 2017 @06:14PM (#15405184)

I have been doing this on Android for a few years using Ivona, FBReader with the FBReader TTS+ Plugin. I got Ivona (beta) from the Play Store before they were bought by Amazon - it looks like Ivona voices have since been pulled and are no longer available.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by exhilaration on Wednesday October 04, 2017 @05:54PM (#15405050)

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

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by mtgx on Wednesday October 04, 2017 @06:29PM (#15405299)

Google's "cloud-based" TTS (not the local one, which was terrible) on the Play Books app was pretty good even years ago.

However, it was unusable because it would stop as soon as the screen would turn-off. Other ebook readers' read-aloud features worked with the screen off. So thanks for nothing Google!

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by andygates on Thursday October 05, 2017 @05:23AM (#15407739)

It used to stop; it's been well-behaved for at least a year. I use it daily!

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by yegle on Wednesday October 04, 2017 @08:29PM (#15405955)

That's not my experience, as I can turn off the screen and still read the book. I tested it just now.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by tommygunz99 on Wednesday October 04, 2017 @09:44PM (#15406218)

Android is different for each person

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by supermdguy on Wednesday October 04, 2017 @06:27PM (#15405286)

For old books, I've liked https://www.librivox.org/, which has free recordings of public domain books read by volunteers.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by michael_h on Wednesday October 04, 2017 @04:42PM (#15404430)

This was kind of the target of the 2016 Blizzard Challenge (http://festvox.org/blizzard/blizzard2016.html), as the training data was children's books (clean audio, 'reading voice' prosody, etc).

Some of the voices that came out of that were incredible.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by rightos on Wednesday October 04, 2017 @04:54PM (#15404546)

Are any of those voices published? Would be interesting to try rendering audio books with them.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by michael_h on Thursday October 05, 2017 @09:19AM (#15408884)

I'm not sure - the exact voices themselves generally aren't published, but the papers are detailed enough that you could recreate the system if you wanted.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by jtsiskin on Wednesday October 04, 2017 @08:30PM (#15405964)

You should check out https://getspeechify.com/ - I use it all the time for exactly this. It also has a great team behind it

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by mark_l_watson on Wednesday October 04, 2017 @09:10PM (#15406115)

Wow, hadn’t thought about that possibility. Too bad for professional narrators of Audible (and other) audio books. I am a happy customer of Audible, and have some favorite narrators. Sad to think that they will lose work.

I am the tech manager for a machine learning team and potentially eliminating jobs is the bad side of my field. That said, I think AI, in some sense of the term, will also help us be more efficient. I imagine everyone having effective assistants that help us in our work, help with communications and scheduling, etc.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by devindotcom on Wednesday October 04, 2017 @06:32PM (#15405315)

Yeah, I was thinking about exactly this. I'm actually going to try to reach out to the team to see if they're going to be looking into this. Google Books on the rise! Hopefully!

Also music generation - the original post (September of last year) had some really interesting music created by training the system on Chopin or something.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by nicklovescode on Wednesday October 04, 2017 @05:21PM (#15404813)

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

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by ThomPete on Wednesday October 04, 2017 @09:07PM (#15406102)

But it will only get better and if humans can learn it...

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by nicklovescode on Thursday October 05, 2017 @06:44PM (#15413127)

I didn't say I was pessimistic on it :)

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by j_s on Thursday October 05, 2017 @12:24AM (#15406676)

Ancient Kindle Keyboard can text-to-speech most Amazon ebooks with zero hassle (I think authors can disable it). 'Unlistenable' is in the ear of the beholder! My only gripe personally is having a single "narrator" for all content.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by riffraff on Thursday October 05, 2017 @02:17AM (#15406976)

I agree "unlistenable" is a personal judgement, but there are very rare cases when buying an audiobook, even with a terrible reader, is not a better value/cost ratio than the original Kindle TTS, it was convenient, but not great.

[ Parent | on HN ]

Re:WaveNet launches in the Google Assistant by justonepost on Wednesday October 04, 2017 @07:09PM (#15405548)

Love this for company documents as well on my commute.

[ Parent | on HN ]