Spotify Has a Secret Weapon–And It May Lead to World Domination
I’ll just tell you what it is: The Echo Nest.
Back in March, Spotify bought it, which is best described as the music industry’s leading “music intelligence company.” The Echo Nest deals in Big Data when it comes to how music moves about the Internet. This information tells Spotify (and others willing to pay for it) important things about how their customers (and potential customers) use digital music. Clear Channel’s iHeart radio, Rdio, SiriusXM, Foursquare, MTV, Twitter and Yahoo are all clients.
Here’s the story of The Echo Nest and how the data it parses moves the needle in the music industry.
Tristan Jehan earned his doctorate in Media Arts and Sciences from MIT in 2005. His academic work combined machine listening and machine learning technologies in teaching computers how to hear and make music. He first earned a Masters in Science in Electrical Engineering and Computer Science from the University of Rennes in France, later working on music signal parameter extraction at the Center for New Music and Audio Technologies at U.C. Berkeley. He has worked with leading research and development labs in the U.S. and France as a software and hardware engineer in areas of machine listening and audio analysis.
Brian Whitman is recognized as a leading scientist in the area of music and text retrieval and natural language processing. He also received his doctorate from MIT’s Media Lab in 2005 in Barry Vercoe’s Machine Listening group and has a master’s degree in computer science from Columbia University’s Natural Language Processing Group. Brian’s research focuses on the cultural analysis of music through large-scale data mining and machine learning.
Scaling and care in managing music related data is, according to Whitman, the basis of The Echo Nest’s work. A greater quantity of music processed, of course, gives more punctual choices for better recommendations. Talent and content is identified regardless of popularity rankings, for that would not help discovering artists. Over two million of them and over thirty million songs get tracked. Apparently no other streaming service or manually edited database in the world has a similar reach. If recommendations are to be creative, moreover, projections have to be made about what the user is intending with his/her search, and this may depend on context. A search for Black Sabbath, for instance, may or may not require pulling Ozzy Osborne’s solo projects.
