Google opens access to its speech recognition API • Hacker News Board

Re: Google opens access to its speech recognition API

#91

Post by jaflo » Thu, Mar 24, 2016, 1:22 AM UTC

Pretty impressive from the limited look the website (https://cloud.google.com/speech/) gives: the fact that Google will clean the audio of background noise for you and supports streamed input is particularly interesting.

I don't know I should feel about Google taking even more data from me (and other users). How would integrating this service work legally? Would you need to alert users that Google will keep their recordings on file (probably indefinitely and without being able to delete them)?

Re: Google opens access to its speech recognition API

#92

Post by mark_l_watson » Thu, Mar 24, 2016, 1:22 AM UTC

discardedrefuse wrote: post #68

mark_l_watson wrote: post #56

Earlier quoted context omitted.

There is a project for Rapberry Pi to use Sphinx to roll your own Amazon Echo like device. You might want to take a look at that.

Mycroft https://mycroft.ai/

Thanks for the link, but this is the Raspberry Pi project: https://github.com/jasperproject

Re: Google opens access to its speech recognition API

#93

Post by skj » Thu, Mar 24, 2016, 1:22 AM UTC

ocdtrekkie wrote: post #53

KyleBrandt wrote: post #46

Earlier quoted context omitted.

As a developer I might be more worried about it not becoming at least amongst the dominant players because they might just drop it. But maybe they only do that with consumer facing items?

Google kills off APIs often. Remember the whole Translate API fiasco? Though that was for overuse, not underuse.

This is a Google Cloud Platform service, and is subject to long deprecation policies at the very least.

Re: Google opens access to its speech recognition API

#94

Post by josephcooney » Thu, Mar 24, 2016, 1:38 AM UTC

I wrote a client library for this in C# by reverse engineering what chrome did at the time (totally not legit/unsupported by google, possibly against their TOS). I have never used it for anything serious, and am glad now there is an endorsed way to do this.

https://bitbucket.org/josephcooney/cloudspeech

Re: Google opens access to its speech recognition API

#95

Post by chetatkinsdiet » Thu, Mar 24, 2016, 1:41 AM UTC

Spooky23 wrote: post #49

saurik wrote: post #3

I think this more directly competes with the IBM Watson speech API, not Nuance?

IBM's offering is using the nuance engine, with Watson using its magic to make more accurate predictions based on context.

IBM split from Nuance a year or so ago- it's now its own engine.

Re: Google opens access to its speech recognition API

#96

Post by chetatkinsdiet » Thu, Mar 24, 2016, 1:42 AM UTC

hardwaresofton wrote: post #25

BorisEm wrote: post #20

Earlier quoted context omitted.

Other "state-of-the-art" speech recognition solutions already exist. For example, Microsoft has been offering it through its Project Oxford service. https://www.projectoxford.ai/speech

Also, CMUSphinx and Julius: http://cmusphinx.sourceforge.net/ http://julius.osdn.jp/en_index.php It is amazingly easy to create speech recognition without going out to any API these days.

As someone who's worked with a lot of these engines, Nuance and IBM are the only really high quality players in the space. CMUSphinx and Julius are fine for low volume operations where you don't need really accurate response rates, but if you want high accuracy neither comes close from my experience.

Re: Google opens access to its speech recognition API

#97

Post by hardwaresofton » Thu, Mar 24, 2016, 1:47 AM UTC

zkirill wrote: post #32

hardwaresofton wrote: post #27

Earlier quoted context omitted.

Came in here to say this (and also include julius), but yeah cmusphinx is awesome.

I haven't seen Julius before, thank you! How do you decide which one to use?

The last time I did interesting stuff with these libs, I used CMUSphinx -- The documentation for Julius wasn't quite good enough yet, and CMUSphinx has great documentation.

Sphinx is supported by Carnegie Mellon and Julius by Kyoto University/Nagoya Institute of Technology.

I think the easier choice even today might still be Sphinx. Given the excellent documentation (they touch pretty much all the basics you need to know), and the availability of pocketsphinx (C) and Sphinx4 (Java).

There's also projects like this: https://github.com/syl22-00/pocketsphinx.js

Re: Google opens access to its speech recognition API

#98

Post by hardwaresofton » Thu, Mar 24, 2016, 1:50 AM UTC

chetatkinsdiet wrote: post #96

hardwaresofton wrote: post #25

Earlier quoted context omitted.

Also, CMUSphinx and Julius: http://cmusphinx.sourceforge.net/ http://julius.osdn.jp/en_index.php It is amazingly easy to create speech recognition without going out to any API these days.

As someone who's worked with a lot of these engines, Nuance and IBM are the only really high quality players in the space. CMUSphinx and Julius are fine for low volume operations where you don't need really accurate response rates, but if you want high accuracy neither comes close from my experience.

Right, but they do offer you a fantastic starting point. If Nuance is 100%, I'd say CMUSphinx is at least 40%.

Also, they give you the tools and knowledge to build better models (and explain the theory), which is where most of the competitive advantage is IMHO.

Re: Google opens access to its speech recognition API

#99

Post by hardwaresofton » Thu, Mar 24, 2016, 1:51 AM UTC

simcop2387 wrote: post #69

ytjohn wrote: post #36

Earlier quoted context omitted.

I first learned about CMUSphinx from the [Jasper Project]( https://jasperproject.github.io/ ). While Jasper provided an image for the Pi, I decided to go ahead and make a scripted install of CMUSphinx. I spent something like 2 frustrating days attempting to get it installed by hand in a repeatable fashion before giving up. This was 2 years ago, so maybe it's simple now, but I didn't find it "amazingly easy" back then…

That sounds like my experience with it from about 5 years ago or so. I gave up on it also. It also didn't help that CMUSphinx has had more than one version in development in different languages.

I would note that as a positive... But yeah, 5 years ago things were much much rougher (which is partly why I didn't think it got so much press).

But these days, if you go all the way through their tutorial, and give it a proper read, it's very doable to set up.

Re: Google opens access to its speech recognition API

#100

Post by hardwaresofton » Thu, Mar 24, 2016, 1:54 AM UTC

blennon wrote: post #67

hardwaresofton wrote: post #25

Earlier quoted context omitted.

Also, CMUSphinx and Julius: http://cmusphinx.sourceforge.net/ http://julius.osdn.jp/en_index.php It is amazingly easy to create speech recognition without going out to any API these days.

Is Julius really state-of-the-art? Looks like they use n-gram and HMMs. Those were the methods that achieve SotA 5+ years ago. My understanding is that Google and Microsoft are using end-to-end (or nearly) neural network models; these outperformed the older methods a few years ago. Not sure how CMUSphinx works under the hood.

They might not be considered state-of-the-art (if you consider both approaches in the same category), but they are definitely one valid approach to voice recognition, which works surprisingly well.

CMUSphinx is not a neural network based system, they do use language and acoustic modeling.