SoylentNews is people
SoylentNews
A decade ago, we in the free and open-source community could build our own versions of pretty much any proprietary software system out there, and we did. Publishing, collaboration, commerce, you name it. Some apps were worse, some were better than closed alternatives, but much of it was clearly good enough to use every day.
But is this still true? For example, voice control is clearly going to be a primary way we interact with our gadgets in the future. Speaking to an Amazon Echo-like device while sitting on my couch makes a lot more sense than using a web browser. Will we ever be able to do that without going through somebody's proprietary silo like Amazon's or Apple's? Where are the free and/or open-source versions of Siri, Alexa and so forth?
The trouble, of course, is not so much the code, but in the training. The best speech recognition code isn't going to be competitive unless it has been trained with about as many millions of hours of example speech as the closed engines from Apple, Google and so forth have been. How can we do that?
[...] Who has a plan, and where can I sign up to it?
Perhaps a distributed computing project (along the lines of Folding@Home, SETI, etc.) would be a viable approach?
(Score: 2) by opinionated_science on Sunday September 25 2016, @05:55PM
there was a product from IBM for voice recognition (ViaVoice), which worked quite well - once trained.
However, tried it on my father (not a native English speaker) - really bad.
Retrained it in my father's language - a definite improvement, and perhaps 90% usable. That was 10 years ago...
I am going to venture the opinion this is a "solved" problem, however the general training matrix (the handwavy Deep Mind BS) might be hard to find without feedback.
For voice recognition to be "good enough", it needs to be engineered to be failsafe - forget robots, you don't want your TV ordering things off the internet!!!
(Score: 2) by frojack on Sunday September 25 2016, @10:25PM
Ibm has never been big in this field.
Nuance (dragon dictate) pretty much owned it until Google launched Google Voice to obtain mountains of voice samples an built their own engine. Google's voice reco is at least as good as Nuance tech (which is used by Apple in the iphone and OSX).
No, you are mistaken. I've always had this sig.