In the world of Internet of Things, it’s easy enough to get something connected to the Internet. But what should you use to communicate with and control it? There are many standards and tools available, but the best choice is always to use the tools you have on hand. [Victor] found himself in this situation, and found that the best way to control an Internet-connected car was to use the Flask server he already had.
The remote controlled car was originally supposed to come with an Arduino, but the microcontroller was missing upon arrival. He had a Raspberry Pi around, and was able to set that up to replace the Arduino. He also took the opportunity to use the expanded functionality of the Pi compared to the Arduino and wrote a Flask server to control it, which is accessed as if you are communicating with a chat bot. Sending the words “go left/forward” to the Flask server will control the car accordingly, for example.
The chat bot itself contains some gems as well, and would be useful for any project that makes use of regular expressions. It also seems to be easily expandable. The project also uses voice commands, and does so by making extensive use of Mozilla’s voice recognition suite. If you want to get deep in the weeds of voice recognition on your own though, you can also explore TensorFlow at your leisure.
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”
The biggest change in Human Computer Interaction over the past few years is the rise of voice assistants. The Siris and Alexas are our HAL 9000s, and soon we’ll be using these assistants to open the garage door. They might just do it this time.
What would happen if you could talk to these voice assistants without saying a word? Would that be telepathy? That’s exactly what [Annie Ho] is doing with Cerebro Voice, a project in this year’s Hackaday Prize.
At its core, the idea behind Cerebro Voice is based on subvocal recognition, a technique that detects electrical signals from the vocal cords and other muscles involved in speaking. These electrical signals are collected by surface EMG devices, then sent to a computer for processing and reconstruction into words. It’s a proven technology, and even NASA is calling it ‘synthetic telepathy’.
The team behind this project is just in the early stages of prototyping this device, and so far they’re using EMG hardware and microphones to train a convolutional neural network that will translate electrical signals into a user’s inner monologue. It’s an amazing project, and one of the best we’ve seen in the Human Computer Interface challenge in this year’s Hackaday Prize.
Your hands are filthy from working on your latest project and you need to run the water to wash them. But you don’t want to get the taps filthy too. Wouldn’t it be nice if you could just tell them to turn on hot, or cold? Or if the water’s too cold, you could tell them to make it warmer. [Vije Miller] did just that, he added servo motors to his kitchen tap and enlisted an AI to interpret his voice commands.
Look closely at the photo and you can guess that he started with a single-lever type of tap, the kind which can be worked with an elbow, so this project was probably just for fun and judging by his video below, he does have a sense of humor. But the idea is practical for dual taps with rotating knobs. He did realize, however, that in future versions he should move the servo motor openings from the top plate to the bottom instead, to avoid any water getting in. A NodeMCU ESP8266 ESP-12E board serves for communicating with the speech recognition side but other than the name, JacobAI, he’s keeping the speech part to himself. We secretly suspect that he has a friend named Jacob.
However, we can think of a number of options for it such as DeepSpeech and Wit.ai which we covered when talking about natural language phone bots, and the ubiquitous Alexa as used here with another NodeMCU for turning on Christmas tree lights.
Continue reading “Talk To The Faucet”
After seeing how Google’s Duplex AI was able to book a table at a restaurant by fooling a human maître d’ into thinking it was human, I wondered if it might be possible for us mere hackers to pull off the same feat. What could you or I do without Google’s legions of ace AI programmers and racks of neural network training hardware? Let’s look at the ways we can make a natural language bot of our own. As you’ll see, it’s entirely doable.
Continue reading “Make A Natural Language Phone Bot Like Google’s Duplex AI”
It has become commonplace to yell out commands to a little box and have it answer you. However, voice input for the desktop has never really gone mainstream. This is particularly slow for Linux users whose options are shockingly limited, although decent speech support is baked into recent versions of Windows and OS X Yosemite and beyond.
There are four well-known open speech recognition engines: CMU Sphinx, Julius, Kaldi, and the recent release of Mozilla’s DeepSpeech (part of their Common Voice initiative). The trick for Linux users is successfully setting them up and using them in applications. [Michael Sheldon] aims to fix that — at least for DeepSpeech. He’s created an IBus plugin that lets DeepSpeech work with nearly any X application. He’s also provided PPAs that should make it easy to install for Ubuntu or related distributions.
You can see in the video below that it works, although [Michael] admits it is just a starting point. However, the great thing about Open Source is that armed with a working set up, it should be easy for others to contribute and build on the work he’s started.
Continue reading “Speech Recognition For Linux Gets A Little Closer”
It’s 2018, and while true hoverboards still elude humanity, some future predictions have come true. It’s now possible to talk to computers, and most of the time they might even understand you. Speech recognition is usually achieved through the use of neural networks to process audio, in a way that some suggest mimics the operation of the human brain. However, as it turns out, they can be easily fooled.
The attack begins with an audio sample, generally of a simple spoken phrase, though music can also be used. The desired text that the computer should hear instead is then fed into an algorithm along with the audio sample. This function returns a low value when the output of the speech recognition system matches the desired attack phrase. The input audio file is gradually modified using the mathematics of gradient descent, creating a result that to a human sounds like one thing, and to a machine, something else entirely.
The audio files are available on the site for your own experimental purposes. In a noisy environment with poor audio coupling between speakers and a Google Pixel, results were poor – OK Google only heard the human phrase, not the encoded attack phrase. Given that the sound quality was poor, and the files were generated with a different speech model, this is not entirely surprising. We’d love to hear the results of your experiments in the comments.
It’s all a part of [Nicholas]’s PhD studies around the strengths and pitfalls of neural networks. It highlights the fact that neural networks don’t always work in the way we think they do. Google’s Inception is susceptible to similar attacks with images, as we’ve seen recently.
[Thanks to Wolfgang for the tip!]