Speech Recognition Geocache: Se Habla Español

Instructables user [jorgegunn] has put a unique spin on a recent geocache build by incorporating speech recognition and requiring that the “finder” knows the secret password to access the loot contained within. Although we won’t spoil the fun here, the techie spirit of the build was further bolstered by choosing a password fitting for any trekkie.

Despite utilizing an off-the-shelf speech recognition circuit kit, the majority of this hack was accomplished using parts available at local electronics and hardware stores. [jorgegunn] went to great lengths to make this hack accessible to any amateur hobbyist  and even includes links to relevant tutorials, schematics, and online parts vendors where applicable.

The actual speech recognition is accomplished with an Images Scientific Instruments model SR-06 circuit kit, capable of recognizing up to 40 different predefined words across multiple languages. Any time a correct match occurs, a value corresponding to the memory slot for that word is displayed on a pair of 7-segment displays. A separate decoder circuit based on a 74LS373 D-Type Latch and 4028 IC Decoder CMOS determines if the value being displayed constitutes a valid response and then drives a solenoid via a Darlington transistor in order to release the latching mechanism. Once opened, the device is simply pushed closed again to await its next finder- we are guessing that finding it might actually be the easiest part as judged by its size!

Although the real-world battery life has not yet been determined, a single coin cell for memory retention and a 9V battery used to drive the circuit and for latch release lasted through a full month of testing without any issues. Battery life could be extended almost indefinitely with a simple solar cell and rechargeable battery setup, but this would also obviously increase the likelihood of vandalism and/or theft.

We can imagine many different applications for such a device as-is including automated door lock  mechanisms and even access control to things such as the controls on a computer case.  It should also be fairly easy to increase the security by stringing multiple words together into a password or by instituting a “time out” period after a certain number of incorrect guesses.

Let us know of any other applications or build variations in the comments below and make sure to see how it all came together in the short videos after the break.

Continue reading “Speech Recognition Geocache: Se Habla Español”

Arduino, RFID, and you

[Matt] has mixed up a batch of two RFID reading door lock systems. While the “door lock” part of the setup has yet to come into existence, the “RFID reading” section is up and running. By using the Parallax RFID readers (for cheap, remember?) and an Arduino, [Matt] is able to parse an RFID tag, look its number up in a database, and then have a computer announce “Access Denied” in a creamy “Douglas Adam’s sliding door of Hitchiker’s Guide” kind of way with Python.

Good books aside, catch a not as exciting as you’re thinking video after the jump.

Continue reading “Arduino, RFID, and you”

Codec2: GNU low-bitrate speech codec

Low bandwidth speech compression is a desirable concept for amateur radio enthusiasts. Unfortunately there isn’t a great open-source option out there, but that’s changing with the low-bitrate speech compression package called Codec2. It manages to transmit and decode at 2550 bits per second with results comparable to proprietary solutions like MELP and very near the initial goal of 2400 bit/s. [David Rowe], who spearheads the project, has been simulating communications using a Linux box and has posted audio snippets at the first link above for comparison. They’re looking for feedback and testing so if you interested give them a helping hand.

[Thanks Robomo]

Get started with speech recognition

Speech recognition makes it easier for us to be lazy with our devices – or perhaps set up the coolest voice-controlled project around. After the voice controlled home automation post, we received a lot of emails asking “how can I make it recognize my voice?”. Whether your project involves a PC or an Android phone, a high-budget, or no budget at all, there is a solution out there.  Join us after the break for a complete set of instructions on setting up speech recognition, and some of the best software options out there to meet your needs.

Continue reading “Get started with speech recognition”

Quad-copter controlled with voice commands

In the video above you’ll see two of our favorite things combined, a quad-copter that is voice controlled. The robot responds to natural language so you can tell it to “take off and fly forward six feet”, rather than rely on a cryptic command set. The demonstration shows both an iPhone and a headset used as the input microphone. Language is parsed by a computer and the resulting commands sent to the four-rotor UAV.

This makes us think of the Y.T.’s robot-aided assault in Snow Crash. Perhaps our inventions strive to achieve the fiction that came before it.

[Via Bot Junkie]

Voice controlled LED sign

120 LEDs and NerdKit, check. Python and appropriate Google Voice module, check. Blend on high for 2 minutes, bake for an hour at 400 degrees Fahrenheit. Your soufflé is done, whoops, we mean your voice controlled LED sign is done. Leave a voicemail on Davis’ Google Voice account that starts with “message” and it will be displayed for all to read within a matter of minutes. We think: make it bigger and add a security code before you can leave a message, and you’ve got the perfect recipe for some over sized message fun.

[via Make]

Vocal mouse control

Absolutely fascinating. The University of Washington is developing a vocally controled mouse interface. We’ve seen vocal control of the computer before, but it is usally responding to specific commands and words to carry out tasks such as opening files.  This system uses different vowels and sounds to create cursor motion.  You can see the same system used in the video above to control a robot arm as well.

[via BotJunkie]