Audio content identification is an essential task for music streaming platforms. It is used for many purposes, including catalog cleaning, innovative product features, or efficient copyright management. Witnessing music delivery rates constantly increasing in the last decade, Deezer has been actively involved in developing and improving its identification methods over the years.
In this study, we will focus on musical versions, defined as “any rendition or performance of an existing musical work”. Identifying two recordings as being versions of the same musical work is quite complex, as many musical dimensions may be heavily affected between both. For instance, new renditions might alter the harmonic, melodic, rhythmic, timbral, or structural content of the original performance, among others. This internship will aim at leveraging lyrics at scale in order to identify versions at scale in a large music catalog.
At Deezer, you can be your true self as we believe that #everyvoicematters. We strive to build an inclusive culture and foster a diverse environment. Because we care and want to ensure each employee feels welcome and safe at work, we continuously focus on fighting biases and helping diverse teams work well together through multiple learning opportunities, e-learnings and workshops right from the onboarding :
Beyond benefits like transportation, we offer you extra perks like:
If you want to learn more about life and culture at Deezer, please visit our Welcome to the Jungle page here!