Engineers design Facebook games to improve music search engineJune 14th, 2009 - 11:28 am ICT by ANI
Washington, June 14 (ANI): Electrical engineers at UC San Diego have designed novel music discovery games on Facebook in order to improve their experimental music search engine that is capable of listening to new songs and accurately labelling them with words-with no help from humans.
The engineers launched the music discovery games on Facebook as an application called Herd It.
“The Facebook games are a lot of fun and a great way to discover new music,” said Gert Lanckriet, the electrical engineering professor and machine learning expert from the UC San Diego Jacobs School of Engineering steering the project.
“At the same time, the games deliver the data we need to teach our computer audition system to listen to and describe music like humans do.
“To play Herd It, log in to Facebook, open the Herd It app, select a genre of music, and start listening to song clips and playing the games.
“Some games ask users to identify instruments, while others focus on music genres, artist names, emotions triggered by the song, and activities you might do while listening to a song.
“The more your answers align with the rest of the online crowd playing the game at the same time, the more points you score,” he added.
“The more examples of romantic songs our search engine is exposed to, the more accurately it will be able to identify romantic songs it has never heard before,” said Luke Barrington, the UC San Diego electrical engineering Ph.D. student leading the project.
“Once enough people play our new music discovery games on Facebook, I’ll have the data I need to both improve our search engine and finish my Ph.D.,” he added.
For the music search engine from UC San Diego to “listen and describe music like a human,” it must find patterns in the songs using the tools of machine learning.
For example, for the system to learn to identify and label romantic songs, it must be exposed to many different romantic songs during the training period. The Facebook games provide the data necessary for the algorithms to learn to label songs on their own.
Once trained, the system can identify romantic songs that it has never before encountered.
The research was presented at IEEE International Conference on Acoustics, Speech, and Signal Processing. (ANI)
- New music playlist algorithm could beat Apple's Genius - Oct 28, 2009
- Inspired by "I, Robot," Indian American student shares top US science prize - Dec 07, 2010
- Computer scientists shatter 'terabyte barrier', set new world record - Aug 01, 2010
- Coconut oil and nano-bombs may help treat acne - Apr 15, 2010
- Short, on-chip light pulses to boost data transfer speeds on computers - Nov 25, 2010
- Robot taught to smile and frown through self-guided learning - Jul 09, 2009
- Fruit fly's response to starvation could help regulate human appetite - Apr 01, 2011
- Breast milk, coconut oil-based face cream may help treat acne - Apr 17, 2010
- How noise pollution affects marine life - Sep 01, 2010
- Search engine statistics can predict human behaviour - Sep 28, 2010
- Rhythm, not genre, is the key to finding music you like - May 20, 2010
- Gene variant linked to glaucoma identified - Sep 22, 2009
- Apple releases iTunes Match - Nov 15, 2011
- Be smart about getting a PhD - Jan 15, 2011
Tags: artist names, computer audition, electrical engineering, electrical engineers, emotions, engineers design, experimental music, facebook, genre of music, jacobs school, june 14, music discovery, music genres, music search engine, new music, new songs, playing the game, romantic songs, school of engineering, uc san diego