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

91–100 of 122 posts

Re: WaveNet launches in the Google Assistant

#91

Post by mark_l_watson »

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"…

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.

Re: WaveNet launches in the Google Assistant

#92

Post by Immortalin »

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"…

Shameless Plug: https://auditus.cc

Uses Amazon Polly for the speech gen

Re: WaveNet launches in the Google Assistant

#93

Post by aikinai »

microcolonel wrote: post #29

Wow, I hear a huge improvement in the Japanese model: the difference between a robot in person and a young woman on the phone.

It's a huge improvement, but still nowhere near the state of the art for Japanese TTS which has always been ahead of English (since the phonetics are much simpler).

Listen to the samples here for example: http://voicetext.jp/samplevoice/

Re: WaveNet launches in the Google Assistant

#94

Post by tommygunz99 »

yegle wrote: post #88
mtgx wrote: post #72

Earlier quoted context omitted.

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!

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

Android is different for each person

Re: WaveNet launches in the Google Assistant

#96

Post by ryansama »

microcolonel wrote: post #29

Wow, I hear a huge improvement in the Japanese model: the difference between a robot in person and a young woman on the phone.

The Japanese wasn't so good.

I like the sound of Risa in http://voicetext.jp better. Try it out the Japanese Google used in their example. If someone knows of a better one it would be great to find out.

一つのウエーブネットのみで、多数の事なら、話者の音声波形極めて正確モデルができます。

Re: WaveNet launches in the Google Assistant

#98

Post by dingle_thunk »

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'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.

Re: WaveNet launches in the Google Assistant

#99

Post by puzzle »

wmf wrote: post #28
chmod775 wrote: post #23

Earlier quoted context omitted.

They literally said it's launching in the Google Assistant (i.e. running on phones) now. In fact that's the title of the article.

Does TTS run on the phone or the cloud?

Google TTS supports both. Maps prefers the cloud one so that you're not at the mercy of whatever TTS your manufacturer has installed (Samsung uses their own, right?), but will fall back to the local one it there's no connectivity. I can't remember if the Google TTS implements that or if it's custom to Maps.

Re: WaveNet launches in the Google Assistant

#100

Post by microcolonel »

aikinai wrote: post #93
microcolonel wrote: post #29

Wow, I hear a huge improvement in the Japanese model: the difference between a robot in person and a young woman on the phone.

It's a huge improvement, but still nowhere near the state of the art for Japanese TTS which has always been ahead of English (since the phonetics are much simpler). Listen to the samples here for example: http://voicetext.jp/samplevoice/

Mm, I see what you mean. It seems like voicetext.jp has more "correct" prosody, and seems to reproduce vocal fry correctly, I'm noticing that's missing from the WaveNet sample now. There's still some work to be done around filtering with voicetext, I hear pretty glaring artifacts between the units, whereas WaveNet doesn't produce any such artifacts.
Post reply on HN