I spent part of my week-end finishing the voice recognition sub-system, tweaking E.V.E’s UX and cleaning up E.V.E / A.D.A.M code. Let’s see how it went ! E.V.E loves snakes E.V.E’s interface is based on HTML5/Javascript and runs inside a browser. I wasn’t too happy with my RPi’s browsers until I settled for Epiphany. Even[…]
Yesterday, I tested a tiny USB microphone for E.V.E, and managed to recognized the recorded sentence with the help of the wit.ai platform (even though the quality of the microphone was a little poor). Let’s get a little deeper into wit.ai and see how it could be helpful for E.V.E. Trying another USB Microphone I[…]
Now that enough progress has been made on E.V.E touch-enabled interface, and since we added a websocket-enabled general purpose middleware (A.D.A.M) to handle local hardware and proxy HTTP requests, we can now tackle voice recognition. The audio sub-system The audio sub-system is probably the weakest point of Raspberry Pi. Without extension (such an USB audio sub-system), only two audio[…]
In the previous post, we quickly reverse-engineered an Orange LiveBox Play set-top box and how it can be easily driven by simple HTTP requests. Be before implementing an interface between E.V.E and this kind of set-top box, we need to sit down and think a bit. Indeed, for now, E.V.E is nothing but a web[…]
Since I’m still waiting for all the audio components I ordered for E.V.E’s voice recognition functionality, let’s try in the meantime to interface E.V.E with a first home device. The very first one that comes to my mind is of course a television set. Let’s try ! Reverse-engineering an Orange Livebox Play set-top box I rely on[…]
Here is a little followup of this week-end work on E.V.E. I’m still at a prototyping stage which means there rough edges and that the source code is sometimes naughty), but it’s getting long nicely. E.V.E is now a Yodeling Cowgirl During this week-end tests, I tried to complete the simple internet radio functionalities of the[…]
E.V.E front panel is touch-based. This is why I ordered an official touchscreen for Raspberry Pi, that I started to play with last night. The software on E.V.E’s front has to run in kiosk mode. There are many alternatives. On could be to use a dedicated framework like Kivy, which can handle multi-touch and be[…]
Since our previous post, the touchscreen and the stand I ordered at Swag shop were delivered (this morning actually). It is now time for an unboxing and a first setup ! The unboxing Two packages were sent via Chronopost: A first one – a very sober white box with no label – containing the 7″ touchscreen[…]
It’s been (yet again) a very very long time since I posted news on “Jarvis”, my pet project on Raspberry Pi. So long I would consider Jarvis project to be almost dead (although it spawned a project internally used at work, but re-baptized “Moshi-Moshi“). Nevertheless, home automation, voice recognition, new forms of human-machine interactions, and[…]
Tonight, I’ll go for a very simple hack: connect a webcam, detect motions and stream a live feed over HTTP. Not sure how it’ll fit with Project “Jarvis”, but who knows … Hardware First things first: the hardware. For some reasons, the only webcam that I had was an old Apple iSight. You know, the[…]
Here comes another step in the conception on project “Jarvis”. For once, let’s not be too geeky. I feel artsy today. I’ll focus on the GUI and fire up Inskcape et the Gimp. Yeah, still a bit geeky, I know… Jarvis-like GUI Let’s try the first idea take comes to my mind: create an[…]
During the last steps, voice recording, speech-to-text and text-to-speech feasibility was studied. Now enters another difficicult part: the brain ! The last steps implied the use of external services for voice-recognition and text-to-speech capabilities. When it comes to Jarvis’ brain, the idea is twofold: Onboard answer engine: part of the analysis will be done onboard[…]
In my previous post, I conducted a few experiments with speech recognition via Google’s Speech API and get enough results to push the project “Jarvis” a bit further. Now it is time for Jarvis to speak ! Text-To-Speech engines There are many “Text-To-Speech” engines already packaged for the Rasberry Pi. Namely: espeak: eSpeak is[…]
Adding Siri to both my old iPad 1 and iPhone 4 was a failure 🙁 Jailbreaking went nice, but messing up with SiriPort was a complete disaster, and it took me nearly 2 hours to turn back these devices into something different than a brick. And thus … no SiriProxy for me. But then[…]
Alright. My Raspberry Pi by is set up and delivering AirPrint and AirPlay services. Let’s add few web capabilities. A lightweight configuration: Nginx & SQLite I felt like the usual Apache / MySQL duet might be a little to heavy for my tiny ApplePie. So, I opted for a Nginx / SQLite couple. Everything[…]
Now that “applepie” (my very first Raspberry Pi) is set up, it is time to have a little fun. The first hacks will be to turn the device into a cheap (but nonetheless quite efficient) AirPlay / AirPrint device, while baking a real Apple Pie… Setting up AirPlay First, I hooked up the Raspberry Pi[…]
It’s been two long weeks, but the Rasberry Pi I ordered finally arrived this friday. I’m extremely excited with this tiny thing. Just like messing with my first computer (30 years ago…) or patching a Linux kernel for the first time. Yep, I really do feel like a kid 🙂 Raspberry Pi The Raspberry[…]