Text2Playlist: Generating Personalized Playlists from Text on Deezer
This addresses the need for better music discovery and personalized listening experiences for streaming service users, though it appears incremental as it builds on existing technologies like generative AI and recommendation systems.
The paper tackled the problem of users needing a smooth listening experience beyond simple search on Deezer by developing Text2Playlist, a tool that generates personalized playlists from text queries using generative AI and music information retrieval, which was successfully deployed at scale.
The streaming service Deezer heavily relies on the search to help users navigate through its extensive music catalog. Nonetheless, it is primarily designed to find specific items and does not lead directly to a smooth listening experience. We present Text2Playlist, a stand-alone tool that addresses these limitations. Text2Playlist leverages generative AI, music information retrieval and recommendation systems to generate query-specific and personalized playlists, successfully deployed at scale.