There was a time when you saw someone walking down the street talking to no one, they were probably crazy. Now you have to look for a Bluetooth headset. But soon they may just be quietly talking to their glasses. Cornell University researchers have EchoSpeech which use sonar-like sensors in a pair of glasses to watch your lips and mouth move. From that data, they can figure out what you are saying, even if you don’t really say it out loud. You can see a video of the glasses below.
There are a few advantages to a method like this. For one thing, you can speak commands even in places where you can’t talk out loud to a microphone. There have been HAL 9000-like attempts to read lips with cameras, but this is power-hungry and video tends to be data intensive.
Continue reading “My Glasses Hear Everything I’m Not Saying!” →
Speech commands are all the rage on everything from digital assistants to cars. Adding it to your own projects is a lot of work, right? Maybe not. [Electronoobs] shows a speech board that lets you easily integrate 255 voice commands via serial communications with a host computer. You can see the review in the video below.
He had actually used a similar board before, but that version was a few years ago, and the new module has, of course, many new features. As of version 3.1, the board can handle 255 commands in a more flexible way than the older versions.
Continue reading “Voice Command Made Mostly Easy” →
If you’ve got a car built in the last 5 years or so, it’s quite likely it’s started by the push of a button when in the presence of a keyfob. Older vehicles make do with the twist of a key. Of course, starting a car by voice command would be cool, and that’s what [John Forsyth] set out to do.
The build uses a Macbook to handle voice recognition, using its Dictation feature. With a hefty download, it’s capable of doing the task offline, making things easier. The dictated words are passed to a Python script, which searches for words like “start” and “go” as a trigger. When an appropriate command is received, the Python script sends a signal over a USB-serial connection to an attached Arduino. The Arduino then toggles a relay connected to the Jeep’s external starter solenoid, starting the vehicle.
As a fan of recent popular films, [John] programmed the system to respond to the command “Jarvis, let’s get things going!”, causing the vehicle to spring into life. There’s room for future improvement, too – the system could benefit from being a little more compact, and there’s a long delay between finishing the sentence and the vehicle starting. A Raspberry Pi and faster dictation software could likely help in this regard.
We’ve seen voice commands used for everything from chess to finding electronic components. Video after the break.
Continue reading “Using Voice Commands To Start A Jeep” →
[Diyguypt] may be an altruist to provide the means for people who can’t manipulate chess pieces to play the game. Or he may just have his hands too busy with food and drink to play. Either way, his voice command chessboard appears to work, although it has a lot of moving parts both figuratively and literally. You can check out the video below to see how it works.
The speech part is handled by an Android phone and uses Google’s voice services, so if you don’t want Google listening to your latest opening gambit, you’ll want to pass this one up. The phone uses an app that talks to the Arduino via Bluetooth, which means the Arduino needs a Bluetooth module.
Continue reading “Voice Chess Uses Phone, Arduino, And An Electromagnet” →
We live in the future. You can ask your personal assistant to turn on the lights, plan your commute, or set your thermostat. If they ever give Alexa sudo, she might be able to make a sandwich. However, you almost always see these devices sending data to some remote server in the sky to do the analysis and processing. There are some advantages to that, but it isn’t great for privacy as several recent news stories have pointed out. It also doesn’t work well when the network or those remote servers crash — another recent news story. But what’s the alternative? If Picovoice has its way, you’ll just do all the speech recognition offline.
Have a look at the video below. There’s an ARM board not too different from several we have lying around in the Hackaday bunker. It is listening for a wake-up phrase and processing audio commands. All in about 512K of memory. The libraries are apparently quite portable and the Linux and Raspberry Pi versions are already open source. The company says they will make other platforms available in upcoming releases and claim to support ARM Cortex-M, Cortex-A, Android, Mac, Windows, and WebAssembly.
Continue reading “Picovoice Puts Smarts Offline In 512K Of Memory” →
We like to think that all these new voice-controlled gadgets like our cell phones, Google Home, Amazon Echo, and all that is the pinnacle of new technology. Enabled by the latest deep learning algorithms, voice-controlled hardware was the stuff of science fiction back in the 1961s, right? Not really. Turns out in around 1960, Ideal sold Robot Commando, a kid’s toy robot that featured voice control.
Well, sort of. If you look at the ad in the video below, you’ll see that a kid is causing the robot to move and fire missiles by issuing commands into a microphone. How did some toy company pull this off in 1961?
Continue reading “Retrotechtacular: Voice Controlled Robot From 1961” →
Websites used to be uglier than they are now. Sure, you can still find a few disasters, but back in the early days of the Web you’d have found blinking banners, spinning text, music backgrounds, and bizarre navigation themes. Practices evolve, and now there’s much less variation between professionally-designed sites.
In a mirror of the world of hypertext, the same thing is going to happen with voice user interfaces (or VUIs). As products like Google Home and Amazon Echo get more users, developing VUIs will become a big deal. We are also starting to see hacker projects that use VUIs either by leveraging the big guys, using local code on a Raspberry Pi, or even using dedicated speech hardware. So what are the best practices for a VUI? [Frederik Goossens] shares his thoughts on the subject in a recent post.
Truthfully, a lot of the design process [Frederik] suggests mimics conventional user interface design in defining the use case and mapping out the flow. However, there are some unique issues surrounding usable voice interactions.
Continue reading “Voice User Interface Design Practices” →