Raspberry Pi Becomes a Universal Translator

hola-me-nombre-david-conroy

We’re still about 150 years away from the invention of the universal translator by [Lt Cdr Sato] of the Enterprise NX-01, but [Dave] has something that’s almost as good: a speech recognition, translation, and text to speech setup for the Raspberry Pi that theoretically allows anyone to speak in sixty different languages.

After setting up all the Linux audio cruft, [Dave] digs in and starts on converting the guttural vocalizations of a meat speaker into something Google’s speech to text service can understand. From there, it’s off to Google again, this time converting text in one language into the writings of another.

[Dave]‘s end result is a shell script that works reasonably well for something that won’t be invented for another 150 years. The video below shows the script successfully translating English to spanish, but it should work equally well with other languages such as dutch and latin, as well as less popular language such as esperanto and french.

[Read more...]

Building a blink based input device

OLYMPUS DIGITAL CAMERA

Fans of the AMC show Breaking Bad will remember the Original Gangsta [Hector Salamanca]. When first introduced to the story he communicates by ringing a bell. But after being moved to a nursing home he communicates by spelling out messages with the assistance of a nurse who holds up a card with columns and rows of letters. This hack automates that task, trading the human assistant for a blink-based input system.

[Bob Stone] calls the project BlinkTalk. The user wears a Neurosky Mindwave Mobile headset. This measures brainwaves using EEG. He connects the headset to an mBed microcontroller using a BlueSMiRF Bluetooth board. The microcontroller processes the EEG data to establish when the user blinks their eyes.

The LCD screen first scrolls down each row of the displayed letters and numbers. When the appropriate row is highlighted a blink will start scrolling through the columns until a second blink selects the appropriate character. Once the message has been spelled out the “SAY!” menu item causes the Emic2 module to turn the text into speech.

If you think you could build something like this to help the disabled, you should check out thecontrollerproject.com where builders are connected with people in need.

[Read more...]

Alert Tube monitors all aspects of your digital life

alert-tube

This futuristic appliance can keep you apprised of all you social network goings on and much more. [Mike Watson] calls the device the Alert Tube because of its functionality and shape. The hardware depends primarily on a Raspberry Pi board which seems tailor-made for this type of use. The information gathering side of this shows off the power of a fledgling services called If This Then That.

We’ve heard of IFTTT only because [Chris Gammel] and [Dave Jones] covered it on an episode of The Amp Hour. [Dave] dismissed it as have little to no practical use. But this project shows how it can be leveraged to make quick work of pulling your desired data from the Internet. Think of it as a collection of APIs for many sites like Twitter, Facebook, as well as local weather, etc. This project sets up IFTTT to monitor your accounts, alerting you with colors of like, sound, and even text-to-speech.

The project explanation is several pages long but you can get a quick look at it by watching the demo video.
[Read more...]

Manuel the Scottish moose speaks your tweets

tod1

The folks over at Torchbox needed a Christmas card this year. Previously, the most poplar holiday card was a web page that gave their visitors a chance to activate a ‘snow machine’ and spray confetti on a random employee, all while being streamed online. They wanted to replicate this bridge between virtual and real life interactions this year, and Manuel the talking moose was born.

Manuel needed a personality and interaction from random people on the Internet so the Torchbox team decided to make the fake moose head speak tweets in real-time with the help of a Raspberry Pi. The code running on the Raspi gets tweets with a #tbxmoose hashtag, sends that through a node.js script, and finally sent to the Festival speech synthesis system.

A few modifications needed to be done to Manuel before he was presented to the Internet. His jaw was chopped in half and a servo and animatronic controller were added for a proper presentation on Torchbox’s stream of Manuel’s random musings.

Twitter radio

twitter-radio

This anthropomorphized wood bowl will read Tweets out loud. It was built by [William Lindmeier] as part of his graduate work in the Interactive Telecommunications Program (ITP) at New York University. View the clip after the break to see and hear a list from his Twitter feed read in rather pleasant text-to-speech voices.

The electronics involved are rather convoluted. Inside the upturned bowl you’ll find both an Arduino and a Raspberry Pi. But that’s not the only thing that goes into this. The best sounding text-to-speech program [William] could find was for OSX, so there is a remote computer involved as well. But we think what makes this special is the concept and execution, not the level of hardware inefficiency.

The knob to the left sets the volume and is also responsible for powering down the device. The knob of the right lets you select from various Twitter lists. Each turn of the knob is responded to with a different LED color in the nose and a spoken menu label. You can get a quick overview of the project from this summary post.

[Read more...]

[Dino's] talking box(es)

[Dino] is about three-quarters of the way through his talking box project. He’s completed one of the two boxes, and is showing off the technique he uses to marry motion with sound in order to mimic flapping lips with the box top.

You may remember [Dino's] first look at the EMIC2. It’s a single-board text to speech module which is what provides the voice for the box. But what fun is that without some animatronics to go along with it? So [Dino] started playing around with different concepts to move the box top along with the speech. This is easier said than done, but as you can see in the video after the break, he did pull it off rather well. He built a motor control circuit that takes the audio output of an LM386 amplifier chip and translates it into drive signals for the motor. The shaft is not directly connected to the lid of the box. Instead it has a curved wire which is limited by a piece of string so that it doesn’t spin too far. It lifts the lid which is hinged with a piece of cloth.

[Read more...]

EMIC2 text to speech module

This is the EMIC2 text-to-speech module. You can see from the logo on the bottom left it’s the latest gadget coming out of [Joe Grand's] Grand Idea Studios. [Dino] tipped us off about his first experience with a prototype of the board. He’s driving it with an Arduino and the video after the break shows that the sound rendering is high quality and the words are very easy to understand. One of the things that we think is interesting is that the serial communications used to drive the board are not uni-directional. In fact, there’s a serial terminal that provides documentation on how to use the chip. Obviously this is most suited to the Arduino, which always has a PC-side terminal window available to it.

[Joe] himself shows some of the potential for the board. He gave new life to a broken toy by replacing its internals with a PIC-based circuit to drive the EMIC2. That video is also found after the break. He’s just using the demo clips, but from that you will get a good idea of the vocal modulations this device is capable of. The board rings up at $60 and is available from Parallax.

[Read more...]