Oregon Team Wins Siemens Competition with Emotion Recognition Project

Computer science research on recognition of emotion in the human voice earned top honors for the team of Akash Krishnan and Matthew Fernandez in the Region One Finals of the 2010-11 Siemens Competition in Math, Science & Technology, the nation's premier science research competition for high school students.

The Siemens Competition, a signature program of the Siemens Foundation, is administered by the College Board. The winners will be invited to compete at the National Finals in Washington, D.C., Dec. 3–6, where winners of six regional competitions will vie for the $100,000 Grand Prize and national acclaim for extraordinary scientific achievement at the high school level.

"Each year, the Siemens Foundation invites America's high school students to make their mark in the world of science," said Jeniffer Harper-Taylor, President of the Siemens Foundation. "We commend these students on rising to the challenge and pushing the envelope of scientific thought."

The students presented their research to a panel of judges from California Institute of Technology (Caltech), host of the Region One Finals.

Akash Krishnan and Matthew Fernandez, juniors at Oregon Episcopal School in Portland, Ore., won the team category and will share a $6,000 scholarship for their computer science project, The Recognition of Emotion in Human Speech.

In their research, the team sought to accurately determine emotion from the human voice. The team was inspired by the movie I, Robot, in which a robot can sense when its user is under stress. Using an emotional speech database with 18,216 files and five emotions (anger, positive, neutral, emphatic, rest), the team developed, trained and tested a classification engine to determine emotions from an input signal. By applying new techniques to emotional speech processing, the team achieved 60 percent accuracy in identifying emotions, well above other researchers' results for the same tests. Emotion recognition has applications in security, lie detection and autism research.

"Recognizing the emotion in a voice is a challenging problem, even for humans. This team took a very creative approach to the problem and made a big leap in performance over previous research," said competition judge Dr. Piotr Dollar, a postdoctoral fellow at Caltech. "They embodied the spirit of what this competition is all about, showing great initiative, independence and teamwork."

Krishnan and Fernandez have been working together as a team since the seventh grade. Dr. Bevin Daglen served as their mentor on the project. While continuing to improve on methods used in their study, the team has filed for a provisional patent and hopes to develop a device that may help autistic children identify and interpret emotions they are hearing. The students indicate they have also had interest in their project from the U.S. government.

The Siemens Competition was launched in 1998 to recognize America's best and brightest math and science students.

Featured

  • Elevate Your Business

    In today’s dynamic business environment, companies specializing in physical security are constantly evolving to remain competitive. One strategic shift these businesses can make to give them the advantage is a full or partial transition to a recurring revenue model, popularly called a subscription service. This approach will bring numerous benefits that not only enhance business stability but also improve customer relationships and drive innovation. Recurring monthly revenue (RMR) or recurring annual revenue (RAR) are two recurring cadence choices that work simply and effectively. Read Now

  • It Always Rains in Florida

    Over the years, and many trips to various cities, I have experienced some of the craziest memorable things. One thing I always count on when going to Orlando is a massive rainstorm after the tradeshow has concluded the first day. Count on it, it is going to rain Monday evening. Expect that it will be a gully washer. Read Now

    • Industry Events
  • Live from GSX 2024 Preview

    It’s hard to believe, but GSX 2024 is almost here. This year’s show runs from Monday, September 23 to Wednesday, September 25 at the Orange County Convention Center in Orlando, Fla. The Campus Security Today and Security Today staff will be on hand to provide live updates about the security industry’s latest innovations, trends, and products. Whether you’re attending the show or keeping tabs on it from afar, we’ve got you covered. Make sure to follow the Live from GSX page for photos, videos, interviews, product demonstrations, announcements, commentary, and more from the heart of the show floor! Read Now

    • Industry Events
  • Playing a Crucial Role

    Physical security technology plays a crucial role in detecting and preventing insider cybersecurity threats. While it might seem like a stretch to connect physical security with cyber threats, the two are closely intertwined. Here’s how physical security technology can be leveraged to address both external and internal threats. Read Now

Featured Cybersecurity

Webinars

New Products

  • AC Nio

    AC Nio

    Aiphone, a leading international manufacturer of intercom, access control, and emergency communication products, has introduced the AC Nio, its access control management software, an important addition to its new line of access control solutions. 3

  • QCS7230 System-on-Chip (SoC)

    QCS7230 System-on-Chip (SoC)

    The latest Qualcomm® Vision Intelligence Platform offers next-generation smart camera IoT solutions to improve safety and security across enterprises, cities and spaces. The Vision Intelligence Platform was expanded in March 2022 with the introduction of the QCS7230 System-on-Chip (SoC), which delivers superior artificial intelligence (AI) inferencing at the edge. 3

  • ResponderLink

    ResponderLink

    Shooter Detection Systems (SDS), an Alarm.com company and a global leader in gunshot detection solutions, has introduced ResponderLink, a groundbreaking new 911 notification service for gunshot events. ResponderLink completes the circle from detection to 911 notification to first responder awareness, giving law enforcement enhanced situational intelligence they urgently need to save lives. Integrating SDS’s proven gunshot detection system with Noonlight’s SendPolice platform, ResponderLink is the first solution to automatically deliver real-time gunshot detection data to 911 call centers and first responders. When shots are detected, the 911 dispatching center, also known as the Public Safety Answering Point or PSAP, is contacted based on the gunfire location, enabling faster initiation of life-saving emergency protocols. 3