How does a submarine talk to an airplane? It sounds like a bad joke but it’s actually a difficult engineering challenge.
Traditionally the submarine must surface or get shallow enough to deploy a communication buoy. That communication buoy uses the same type of radio technology as planes. But submarines often rely on acoustic transmissions via hydrophones which is fancy-talk for putting speakers and microphones in the water as transmitters and receivers. This is because water is no friend to radio signals, especially high frequencies. MIT is developing a system which bridges this watery gap and it relies on acoustic transmissions pointed at the water’s surface (PDF warning) and an airplane with high-precision radar which detects the oscillations of the water.
The complexity of the described setup is mind-boggling. Right now the proof of concept is over short distances and was tested in a water tank and a swimming pool but not in open water. The first thing that comes to mind is the interference caused by waves and by aerosols from wind/wave interactions. Those challenges are already in the minds of the research team. The system has been tested to work with waves of 8 cm (16 cm measured peak to trough) caused by swimmers in the pool. That may not sound like much, but it’s about 100,000 times the surface variations being measured by the millimeter wave radar in order to detect the hydrophone transmissions. Add to that the effects of Doppler shift from the movement of the plane and the sub and you have a signal processing challenge just waiting to be solved.
This setup is very interesting when pitched as a tool for researching aquatic life. The video below envisions that transmitters on the backs of sea turtles could send communications to aircraft overhead. We love seeing these kinds of forward-thinking ocean research projects, like our 2017 Hackaday prize winner which is an open source underwater glider. Oceanic studies over long distances have been very difficult but we’re beginning to see a lot of projects chipping away at that inaccessibility.
Continue reading “Submarine to Plane: Can You Hear Me Now? The Hydrophone Radar Connection”
Star Trek has its universal language translator and now researchers from Facebook Artificial Intelligence Research (FAIR) has developed a universal music translator. Much of it is based on Google’s WaveNet, a version of which was also used in the recently announced Google Duplex AI.
The inspiration for it came from the human ability to hear music played by any instrument and to then be able to whistle or hum it, thereby translating it from one instrument to another. This is something computers have had trouble doing well, until now. The researchers fed their translator a string quartet playing Haydn and had it translate the music to a chorus and orchestra singing and playing in the style of Bach. They’ve even fed it someone whistling the theme from Indiana Jones and had it translate the tune to a symphony in the style of Mozart.
Shown here is the architecture of their network. Note that all the different music is fed into the same encoder network but each instrument which that music can be translated into has its own decoder network. It was implemented in PyTorch and trained using eight Tesla V100 GPUs over a total of six days. Efforts were made during training to ensure that the encoder extracted high-level semantic features from the music fed into it rather than just memorizing the music. More details can be found in their paper.
So if you want to hear how an electric guitar played in the style of Metallica might have been translated to the piano by Beethoven then listen to the samples in the video below.
Continue reading “Facebook’s Universal Music Translator”
by: [Hideyuki Yamamoto] based on this feature.
3Dプリンターメーカーが小さくて精度が高いプリンターを開発するのに躍起になっている中でShanghai WinSun Decoration Design Engineering Companyという中国にある会社がオリンピックプールの半分程度の大きさの巨大な3Dプリンターで実験を重ねているとBBCなどは報じている。
Continue reading “Japanese Edition: 3Dプリンターで24時間以内に住宅建設。しかもリサイクル材料を用いたエコ建築。”
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.
Continue reading “Raspberry Pi Becomes a Universal Translator”
[Will Powell] sent in his real-time subtitle glasses project. Inspired by the ever cool Google Project Glass, he decided he would experiment with his own version.
He used two Raspberry Pi’s running Debian squeeze, vuzix glasses, microphones, a tv, ipad, and iphone as the hardware components. The flow of data is kind of strange in this project. The audio first gets picked up by a bluetooth microphone and streamed through a smart device to a server on the network. Once it’s on the server it gets parsed through Microsoft’s translation API. After that the translated message is sent back to a Raspberry Pi where it’s displayed as subtitles on the glasses.
Of course this is far from a universal translation device as seen in Star Trek. The person being translated has to talk clearly into a microphone, and there is a huge layer of complexity. Though, as far as tech demos go it is pretty cool and you can see him playing a game of chess using the system after the break.
Continue reading “Real Life Subtitle Glasses”