Donate to Science & Enterprise

S&E on Mastodon

S&E on LinkedIn

S&E on Flipboard

Please share Science & Enterprise

Robot Recommends and Plays Music Based on Listener Feedback

Gil Weinberg (Georgia Tech)

Gil Weinberg (Georgia Tech)

A robotic device developed at Georgia Institute of Technology, and licensed to a start-up company in Atlanta, can recommend songs based on listeners’ tastes, and even dance to the music selected. Shimi, a musical companion derived from technology developed at Georgia Tech’s Center for Music Technology, is expected to be demonstrated today at Google’s I/O Conference in San Francisco.

Shimi is a one-foot tall docking station for an Android smartphone that gains the sensing and musical generation capabilities of the owner’s mobile device. The device uses the phone’s camera and face-detecting software to follow a listener around the room and position its speakers for optimal audio reception.

Shimi can also recognize rhythm and tempo, from ambient tapping or clapping, but also from the phone’s music library. If the phone’s owner claps in a certain rhythm, Shimi analyzes the beat, then scans the phone’s stored music and plays the song that best matches the suggestion. And once the music starts playing Shimi, dances along to the music.

“If robots are going to arrive in homes, we think that they will be these kind of machines: small, entertaining, and fun,” says Gil Weinberg, professor of music at Georgia Tech and director of the Center for Music Technology. Georgia Tech has licensed the technology behind Shimi for commercialization to Tovbot, a company formed earlier this year by Weinberg and partners from MIT’s Media Lab and IDC Herzliya in Israel.

Shimi’s dancing ability will be on display at Google’s I/O conference. The following video gives a preview of three Shimis doing their dance routine.

Read more:

*     *     *

1 comment to Robot Recommends and Plays Music Based on Listener Feedback