After comparing various speech to text engines, and staring at transcripts, I got intrigued about how much more metadata I was getting back from Watson about the speech. With both timings and confidence levels I built a little visualizer for the transcript that colors things based on confidence, and attempts to insert some punctuation:
This is a talk by Neil Gaiman about how stories last at the Long Now Foundation.
Things are more red -> yellow based on how uncertain they are.
A few things I learned along the way with this. Reversing punctuation into transcriptions of speech is hard. Originally I was trying to figure out if there was some speech delay that I could guess for a comma vs. a period, and very quickly that just turned into mush. The rule I came up with which wasn't terrible is to put a comma in for 0.1 - 0.3s delays, and put one period of an elipsis in for every 0.1s delay in speech for longer pauses. That gives a sense of the dramatic pauses, and does mentally make it easier to read along.
It definitely shows how the metadata around speech to text can make human understanding of the content a lot easier. It's nice that you can get that out of Watson, and it would be great if more environments supported that.
As the Supreme Court considers extending same-sex marriage rights to all Americans, we look at the patterns of social change that have transformed the nation.
Source: This Is How Fast America Changes Its Mind | Bloomberg Business - Business, Financial & Economic News, Stock Quotes
Really interesting visualization and look at how social issues hit a tipping point far faster than one might expect, and then the federal government just steps in and unifies things. Love looking at data sets like this.
Very cool interactive graph visualizing temperature anomalies reported in the US from 1964 to current. The full site gives all the data they used and methodology for the analysis.
I love visualizations, and quite enjoyed this new tool by Linked In. It did a pretty good job on the clustering, blue is IBM, green is OpenStack, red is Wesleyan, the purple at the bottom is basically 3D internet/OpenSim folks, and the orange/grey lobe is MHVLUG and other local folks in the area.
You can generate your own one here.
Thanks to XKCD for making this Radiation Chart available on the web. This will help you visualize and understand the various levels of radiation. Simple things to know, you get 3x the amount of radiation by living 50 miles from a Coal plant than you do from living 50 miles from a Nuke plant.
...because I've seen this a couple of places now, and more people should realize that cutting taxes on > 90% of americans is being called raising taxes by the media.
...because expanded offshore drilling isn't going to do anything except destroy the rest of our fishing industry.
Above is one of the many cool visualizations already in many-eyes (direct link here for rss readers that don't display it), a social visualization site from IBM. I'd heard a little bit about the site but after today's session at MIT thought it was time to check it out further. It's a little slower than I like, but pretty neat regardless. Plus, the Pork / Capita numbers are pretty telling.
Here's what my delicious links look like via wordle:
I'm amused, and love visualizations like this.