Smaragdis Named an IEEE Fellow

CS Assistant Professor Paris Smaragdis was recently named a Fellow of IEEE “for contributions to audio source separation and audio processing.”

Paris Smaragdis

Being named an IEEE Fellow is a distinction reserved for select IEEE members whose extraordinary accomplishments in any of the IEEE fields of interest are deemed fitting of this prestigious grade elevation. IEEE is the world’s largest technical professional society.

“I am very honored to have received this distinction,” said Smaragdis, who has a dual appointment with the Department of Electrical and Computer Engineering. “Knowing that this comes from my peers is particularly gratifying, as is receiving this from such a well-established and respected organization.”

In his research Smaragdis focuses on computational foundations for constructing systems that can understand sound (e.g., speech or music) the same way people do. He attacks these problems from both theoretical and a practical sides.

On the theoretical side this involves creating new tools for processing and analyzing time-series, and draws heavily from the fields of machine learning and statistical signal processing. On the practical side this results in constructing actual machines with hearing abilities such as TVs that can find when the football game gets interesting, stethoscopes that detect and analyze heartbeats, music players that automatically DJ for you and smart traffic lights that can hear accidents that happen in their intersection.

Smaragdis has created a demonstrations page that illustrates some of the work he has done, including audio interface, source separation, video content analysis using sound, filling in missing data, and source localization.

“I find the automatic understanding of sound endlessly fascinating, especially since we don’t really know how we hear ourselves, so making machines that can do so is quite an adventure,” said Smaragdis. “Nowadays, we are constantly surrounded by microphones (cellphones, laptops, cameras, etc.), we find even more exciting research prospects in computational audition, as we try to consolidate massive amounts of uncurated acoustic data and combining them so as to make sense of our environments. Thankfully we have our work cut out for the next few decades!”

In 2006 Smaragdis was selected by MIT Technology Review as one of its Innovators under 35.