Re: Speech recognition system for Home automation.

[Marc_F_Hult <MFHult@xxxxxxxxxxxxxxxxxxxxx>]

On Wed, 12 Sep 2007 08:52:06 -0700, RickH <passport@xxxxxxxxxxxxxxxxxxxxx>
wrote in message  <1189612326.338870.9210@xxxxxxxxxxxxxxxxxxxxxxxxxxxx>:


>Ideally I'd like to see Insteon keypad/paddle switches with a mic and
>local voice recognition that allow you to enter a few dozen words that
>simply map to the hard switches, for dual voice/finger control.  All
>self contained in a voice chip, no computer.  If you can make one of
>those, I'd buy it.  It should also of course have a way to disable/
>enable voice control for the switch, and it should at least be
>trainable to support the voices of 4 different persons.  So a typical
>8 button keypad would need room for 40 voice commands (5 per switch)
>
>click (toggle)
>on (explicit on for convenience)
>off (explicit off for convenience)
>holddown (for dim brt)
>letgo (to end dim brt)
>
>(or whatever voice commands make sense for what your fingers would be
>doing)
>
>times 4 people, so 160 programmable voice commands.
>
>With switches like this it would be a snap to make an entire home
>voice controllable, as the numerous localized microphones would
>increase dependability with ambient noises and be more intuitive as to
>what part of the wall/room you need to talk to.
>
>The deluxe model of such a switch can also contain a proximity sensor
>that will only enable "listening" when there is a human within 10 feet
>or so (adjustable).
>
>These would be great for handicapped homes, etc where getting to the
>switch alone might be a chore.  Downstream loads can then respond to
>normal Insteaon or X10 switch mappings.
>
>Can you make one of these given that Insteon is a licenseable chip and
>you already seem to have a handle on the voice chip?
>

Hi Rick,

This would have to be built at very high volume to be commercially
feasible.  And as much as I like INSTEON (and use it, and am a registered
developer) a direct-connection (electrical) hook to INSTEON dimmer or
switch would not be covered under the existing code approval for the
INSTEON device. That in itself is a deal-breaker even if there were a handy
plug/patch/connection available (which I don't think there is).

A different approach that I've worked on for years is a home-brew lighting
system that uses local motor-driven mechanical potentiometers for lighting
control.

The latest version of the on-motor controller board has a pair of pins that
control the UP / DOWN motor function that is intended for local, add-on
control. That is to say, they are not needed by the centralized control
system and can be used in conjunction with local sensors.

My immediate application is to add autonomous (not controlled by central PC
or MCU) local ambient light control and local IR remote. And they would
serve just as well for local control by RF signal or by speech.

The architecture of the system is such that regardless of whether changes
to lighting level are made by rotating a knob,  moving a slider, voice
control, a local ambient light sensor, IR remote or RF signal, the central
PC is updated about 40 times a second as to the actual dimmer control
signal (+/- 0.5%). This is done with an analog signal that is easily
trouble-shot and DMX (DMX512a; DMX-512)  which is ubiquitous international
standard for hard-wired entertainment (theatre, club etc) and architectural
lighting.  I don't know of any other system -- commercial or not -- that is
as flexible as what I've designed for home use.

Of probably wider interest, I am also working on a potentiometer version
that provides a  _local_ AC dimmer retrofitted to unmodified, existing AC
wiring using a UL-listed solid state dimmer/relay and thus is compliant
with the National Electrical Code -- AHJ willing.

An existing switch (eg: X-10 WS467, or manual SPST toggle ) is replaced
with a single or dual random phase, UL-listed solid state relay inside the
existing switch box. Only two AC wires -- no neutral -- are required. The
zero-crossing signal is derived remotely and so only a pair of low-voltage
wires carrying the switch signal, optically isolated inside the SSR, is
needed. As this geologist understands it, this configuration is fully
1996-and-later NEC compliant.

One way the potentiometer(s) w/could be mounted is to a new faceplate
attached to the existing switch box with a blank (no opening) over the AC
portion. The faceplate would be one gang wider that the existing plate. The
pots would be on the added portion and fit into a cut-out in the wallboard
to the left or right of the switch box depending (usually) on which side of
the switch box the stud was. But no rearrangement of the AC wires or switch
box itself would be needed. One would, of course need to run CAT5 to the
switch, but that is typically much easier than replacing AC wiring.

These are planned for installation initially in my house in those locations
where INSTEON cannot be used without running new AC electrical owing to the
absence of a neutral conductor, and ultimately, to replace INSTEON.

I'll post some of the PCBs and descriptions on my web site.

... Marc
Marc_F_Hult
www.ECOntrol.org