Creating Systems that Listen Intelligently

Primary tabs

Researchers at Georgia Tech are developing technologies to advance human interaction with music.

Music Professor Parag Chordia says that technology is transforming the way we listen to music, the way we discover music and the way we create it. His research focuses on building systems that can listen to music and respond intelligently. The artificial intelligence is designed to analyze the 'musical DNA' of songs, using techniques from machine learning and signal processing to find the hidden patterns in the music.

"We're trying to create intelligent technologies that will make people's interaction with music more satisfying and enjoyable," said Chordia. "At the end of the day, music is one of those transcendent phenomena that lifts us up and makes life worth living."

According to Chordia, technology can play a role in music discovery by recommending new music to listeners, and in music creation, allowing non-musicians to experience the joy of musical performance.

"Right now there are tens of thousands of songs released each year. Technology can be a 'personal ear' and help someone find music they love," said Chordia. "Technology can also be a virtual band for a guitar player by listening to what is being played and creating the appropriate accompaniment."

Chordia's research also includes a collaboration with Melody Moore Jackson, adjunct associate professor in the School of Interactive Computing, in which brain imaging techniques are used to learn how the brain reacts during the creative process.

"We're looking at whether specific patterns of brain activity correspond to specific musical tasks," said Chordia. "I'm particularly interested in improvisation and what happens in the brain when a person is creating music on the fly."

Chordia said he hopes to apply what he learns from the research on music creativity to engineering and other art forms as well. "Music is a form of creative problem-solving, which is relevant for many other situations that require us to make real-time decisions in dynamic environments."

 

Groups

Status

Categories

  • No categories were selected.

Keywords

  • No keywords were submitted.