Re: Speech recognition system for Home automation.

[Soren <soren.skou.nielsen@xxxxxxxxx>]

On Sep 18, 3:15 am, "Robert Green" <ROBERT_GREEN1...@xxxxxxxxx> wrote:
> "D&SW" <d...@xxxxxxxxxxx> wrote in message news:tmEHi.11654
> > I don't know that speech recognition is "a simple task". Try googling and
> > ebay'ing for "Mastervoice" or "Butler-in-a-Box",  old technology but
> worked
> > well.
>
> It's simple - in a lab.  And it's readily available, too.  I checked Google
>
> http://www.google.com/search?hl=en&safe=off&q=stand+alone+speech+reco...
> +systems+-patents
>
> and there's a whole host of solutions out there.  The biggest problems,
> IMHO, are that some lifestyles and homes are not compatible with voice
> commands.  If you have music or TV playing in the background, the problem
> gets pretty complex and requires the speaker be very close to the
> microphone.
>
> Probably the best method currently would be to use a cordless phone system
> to link to the speech controller since most people have phones in multiple
> rooms these days.  Not quite the hands free technology-as-magic but probably
> far more reliable than any current roomwide mic setups.  People have been
> able to get such roomwide installations to work, but it's a lot of effort
> and still isn't immune (or as immune) to loud ambient noise as a good phone
> mic placed close to the speaker's mouth.
>
> It's possible to mute the electronic audio or attempt to mute it via noise
> cancellation, but I think the voice commanded home is still a bit off in the
> future.  It's a little bit like the leap that was supposed to occur nearly
> 30 years ago when holograms were invented.  The pundits predicted that in a
> few short years, all photos would be holographic and all movies made in 3D.
> Aside from a segment in the movie "Logan's Run" I haven't seen much progress
> in the world converting to 3D imaging.  (-:
>
> Eventually, we'll be able to separate the loud background noise from the
> speaker's voice - hell, my *dog* can do it right now!  More likely we'll all
> be wearing invisible headphone and mics that tie us into the net, our phones
> and our house, but it's taking longer than expected, at least from where I'm
> sitting.  But it's starting.  I see a lot more people every time I go out
> with Bluetooth earpieces stuck in their ears.
>
> --
> Bobby G.

Research has already reached a point where you can get very good
speech recognition down to a SNR of 10 dB. This article got around 80%
correct for a 10 dB SNR (http://www.ee.ucla.edu/~spapl/paper/
cui_fcpoly.pdf), ok it's in the lab, but they also tested different
noise types, like restaurants, airports, etc. Now, noise at home is
rarely at the level of a restaurant.. or an airport :) (at least if
you don't have kids) Theres no doubt in my mind that signal processing
algorithms will reach a level where speech recognition will even work
well in heavy noise, and it's not in the too distant future. Of
course, beating the human hearing is not around the corner.. if you
can't understand what a person is saying while the TV is on, then most
likely neither can the computer. There are already home speech
recognition systems, like the butler-in-a-box, that provide noise
robust speech recognition to some extent. I'm certain that the
algorithms today have reached a level that makes robust speech
recognition in your home, with moderate noise possible, and i'm not
surprised if such systems already exists and works well. I just want
to see how good/bad a REALLY cheap DIY system works :)

Soren