live

One of our favorite things in the world is when animals decide to interrupt random formal events - whether it's a cat crashing a baseball field in the game, a cat deciding to randomly show up on a runway and show up all of the models by having a better strut than them. Or, of course, when animals decide that whatever news is being reported is not that important - they need to be the stars instead. 

This doggo is definitely the star of this news report, we can say that confidently. Coming in all dramatically, stealing this unsuspecting reporter's mic, and sending her running off into the distance to get it. It's amazing. We love this dog. And so does this reporter. 

Henry Conklin loves his dog and wants to share the canine's voice with the world. Modern social media and Conklin's technological know-how make that possible.

The mathematics/computer science undergraduate student at the University of Virginia regularly engages in competitive programming and decided to use these skills to make a Twitter account that his dog Oliver could 'control'.

@OliverBarkBark tweets every time Oliver barks. So far he's had some very insightful things to say:

Conklin describes the process by which he achieved this feat on his website:

By connecting a Rasberry Pi, a wifi dongle, and a microphone, I was able to make a system that automatically detected, filtered, and published each and every one of Oliver's deafening vocalizations.

The full process from bark to tweet takes three steps. First is recording. I have the raspberry pi listening continuously and triggering a recording once it hears a sound over a preset volume. Oliver barking is by far the loudest thing within several miles, so the volume threshold should be sufficient. However, the recordings are still triggered occasionally by unwanted junk. To guard against this, I needed to perform a second step to filter the barks from the junk.

I took a machine learning approach to filter out the barks. I built a model using the pyAudioAnalysis library and around a day's worth of barks (about 20). I then set up a bash script to run every ten minutes, classify each recorded sound, and forward the barks on to the next step.

Finally, the barks are forwarded to the twitter api (using python-twitter) and posted under the handle @OliverBarkBark (be sure to follow!). Currently the tweets are random strings composed of "bark," "ruff," and "woof." I plan to replace that with a bark-to-text translator that will likely produce similar results but be more accurate to Oliver's actual voice.

Being the cool guy that he seems, Conklin also made all the code it took to accomplish this publicly available.

He said the next step is puppy podcasting.

WE DOAN'T HAB TIEM TO DISCUSS THE LOGISTICS OF ME DRIVING WITHOUT BEING ABLE TO REACH THE PEDALS - GET IN!!

THINGS YOU NEED TO KNOW:

1) CORGIS! 2) 24/7 LIVE COVERAGE... OF CORGIS! 3) TWO-WEEK-OLD CORGIS! 4) CORGIS!!!!!!!!!11 5) SLKSU$LAJLKSDJFHSLKHSLOMFGSOCYOOOOTTTTTTTCORGISSSSSS!

David Bowie's wig from Labyrinth suddenly took on a life of its own.

Maek wae foar da homo superior!!

Live nine lives and prosper

Live Long And Prosper