The Voice Recognition Typewriter

Typewriters with voice recognition have existed for over one hundred years; they were called secretaries. Robots are taking all the jobs now, and finally dictation and typing is a job that can be handled by a computer. [Zip Zaps] used an old Smith Corona typewriter to automate the process of turning dictation into print. Like a secretary hunched over an anachronistic IBM Selectric in the first season of Mad Men, this robot will take dictation and accept the overt sexism of a 1960s Manhattan ad agency.

Instead of the machinations of a few biological actuators, this typewriter is controlled with an array of servos driven by Pololu Maestro servo controller. There are twelve servos that move a small actuator down onto the keys, and another twelve servos that move the others above the correct row of the keyboard. The carriage return lever is actuated by a stepper motor, linear rail, and giant plastic lever.

While a robot that can use a typewriter is impressive, the real trick is getting it to take dictation. [Zip Zaps] used the built-in voice recognition found in Windows for this, streaming characters over a serial port to the Arduino-based electronics.

Does it work? Yes, surprisingly it does. Is it useful? Well, typewriters naturally have a cleaner, more analog tone about them, and you can’t replicate the typing experience of an old Smith Corona typewriter with a digital format. This build is just the natural extension of what digital electronics are capable of these days, and we look forward to seeing someone with this amazing device in our local Starbucks.

Continue reading “The Voice Recognition Typewriter”

Amazon’s AI Escapes Its Hardware Prison

It’s the 21st century, and we’re still a long way from the voice-controlled computers we were all promised in the 60s, 70s, 80s, and 90s. The state of voice interaction has improved, though, and Amazon’s release of the Alexa Skills Kit (ASK) is another sure step towards a future of computers that will pay attention to you. This allows any hardware to become Alexa, your personal voice assistant with the ability to do just about anything you command.

amazon_echoUp to this point, Alexa was locked away inside the Amazon Echo, the ‘smart’ cylinder that sits in your living room and does most of what you tell it to do. Since the Amazon Echo was released, we’ve seen the Echo and the Alexa SDK used for turning lights on and off, controlling a Nest thermostat, and other home automation tasks. It’s not Google Now, Microsoft’s Cortana, or Apple’s Siri that is behind all these builds; it’s Amazon’s Alexa that is bringing us into a world where Star Trek’s [Scotty] talking into an old Mac is seen as normal.

Right now, the Getting Started guide for the Alexa Skills Kit is focused more on web services than turning lights on and air conditioning off. Sample code for ASK is provided in JavaScript and Java, although we would expect 3rd party libraries for Python to start popping up any day now. If you want to run ASK on a Raspberry Pi or other small Linux computer, you’ll need a way to do voice capture; the Jasper project is currently the front-runner in this space.

We hope this changes the home automation game in a couple of different ways. First, the ASK processes everything in the cloud so very low power devices are now ready for some seriously cool voice interaction. Second, Amazon’s move to open up what you can do with the software backend means a community developing for the hardware could eventually exert pressure on Amazon to do things like making the system more open and transparent.

Already working on some hacks with the Echo or ASK? Send in a tip to your write-up and tells us about it in the comments below.

Talkbot: An Arduino-driven Robot For Beginners

talkbotguts

It isn’t exactly WALL-E, but [Bithead’s] affordable introduction to robots — Talkbot — is made out of a trash can. This little guy runs off an Arduino and comes packed with features, including a voice chip, a motor shield, and a pair of bump sensors. Talkbot will cruise around until a bump sensor slams into an obstacle. One of his prerecorded messages will then play through the speaker while he backs up, turns, and tries to find a clearer path.

According to [Bithead’s] build log, tracking down the right bargain voice chip was a bit of a hassle; he skipped over the text-to-speech options only to be stalled by vendor issues. He finally settled on a clone of Sparkfun’s WTV020SD chip sourced from eBay, which allows you to access pre-recorded WAV files stored on a Micro-SD card. The robot’s body comes straight off the hardware store shelf, with PVC pipe for arms and a polystyrene base to hold all the parts.  At the bargain price of $110, [Bithead’s] students will have a true hacker experience cobbling the Talkbot together rather than using a prefab kit.

Be sure to see Talkbot  in a video below, performing either his green-eyed “friendly mode” or red-eyed “grumpy mode,” which dictates how pleasantly he responds to obstacles. Need something more advanced? Check out the tentacle robot, just in time for Halloween.

Continue reading “Talkbot: An Arduino-driven Robot For Beginners”

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]

Headset and microphone

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”