Pre-Ramble: I love hearing stuff about kids who are crazy good at science. Yesterday’s NY Times Magazine (Sunday, 2/27) featured “Youth.” Two of them, Matt Fernandez and Akash Krishnan, friends from Portland, Oregon, had built a computer program that can recognize “feelings” in human speech patterns for their high school science fair.
In a nut-shell, the very cool algorithum that they came up with determines emotion in spoken words by measuring 57 different aspects of an audio signal as compared to a signal that has been pre-defined as a specific emotion - such as “fear, anger, joy and sadness.”
“Computers have become very good at parsing an audio signal into specific words and identifying their meaning. But spoken language is more than just semantics… it’s far from clear what elements in an audio signal indicate happiness or anger as a quality of voice. Trying to figure that out quickly consumed them. Matt stayed up late reading research papers, ignoring his other homework … Akash was up until 3 a.m. many nights reading and programming… The research paper they submitted for the [science fair] was 30 pages of code and 60 pages of writing to explain it.”
Matt and Akash ended up taking first place at the science fair; went on to represent their school at the Intel International Science and Engineering Fair in San Jose; entered the Siemens Competition (one of two premier science competitions in the country); won the team grand prize at the national competition in Washington; and their program has been linked to practical applications such as a way to help autistic children recognize emotional cues in speech, and to provide emotion recognition capabilities for cell phones and other interactive devices.
Nice going, boys!! …
But, I digress … The work of these gifted young scientists harkens me back to reflect upon the efforts of another young scientist … less brilliant perhaps, but toiling away nonetheless in her Environmental Living 101 class at the University of Michigan in the late 1970′s.
As you can imagine, in this nearly pre-historic time, there were no computers … no internet … really no “technology” to speak of, unless you want to count calculators (ha!). We were practically using the stone and chisel.
The scientific challenge was to create a “parabolic reflector” (an umbrella lined with aluminum foil, poked upside-down into the grass to catch the sunlight) which would harness solar power in amounts strong and focused enough to cook a standard cupcake. (I blame my parents for the selection of this particular research topic, as I was never allowed to have an Easy Bake Oven … Curiously, years later, when faced with this scenario with my own young daughters, I forbade them from owning or consuming the disgusting packets of chemicals that foamed together under the heat of a light bulb as well.)
The archived project notations are sketchy, however, as I recall, the strength of the sunlight in early April in the northern Midwest left much to be desired, (not even a boost of global warming to help it along). Due to either the ravages of radiant temperatures in the precisely calculated “hot spot” of the reflector, or simply drying out in the air, the cupcake (chocolate) ended up being barely edible.
The Take-Away: My point here, is that there are lots of curious, talented kids out there just waiting for an opportunity to explore some odd notion that crosses their mind. Matt and Akash were obsessed in their quest to get to the bottom of the emotion recognition challenge … Every kid, even the ones who aren’t pre-inclined to math and science geekiness, has to be wondering about something? Whether their inquiry results in a patent-worthy method of digital emotion recognition or a petrified cupcake, we, as a society, need to foster both the curiosity and the opportunity for kids to engage in exploration of ideas.
Post-Note: I want more of my tax dollars to go into the “curiosity and opportunity”/education bucket and less to go into the “get involved in another foreign war” bucket.