Today, music is typically categorized by artist genres (Rock, Hip Hop, etc.). However, artist genres alone do not always tell the full story of an artist's full catalog or career. Gracenote Sonic Style looks far beyond industry-standard artist-level genre categories by looking at each recording individually and drilling into its unique musical style. For instance, Taylor Swift is traditionally classified as simply Pop or Country. However, many of her more recent tracks have a more Pop Electronica and even R&B feel to them.
By distinguishing Sonic Style at the recording level, streaming music providers can better select the most relevant, engaging and personalized tracks for each listener, spanning multiple eras, based on their unique style preferences. Further, record labels and music publishers can gain a deeper understanding of which underlying music styles are driving listening trends around the world.
“Now that playlists are the new albums, music curators are clamoring for deeper insights into individual recordings for better discovery and personalization," says Brian Hamilton, General Manager of Music and Auto for Gracenote. “To achieve scale, Sonic Style applies neural network-powered machine learning to the world's music catalogs, enabling Gracenote to deliver granular views of musical styles across complete music catalogs. These new turbo-charged style descriptors will revolutionize how the world’s music is organized and curated, ultimately delivering the freshest, most personalized playlists to keep fans listening."
By applying machine learning to music produced by major and indie labels, Gracenote Sonic Style is now able to quickly classify the largest catalogs, scaling to cover all types of music content from popular artists as well as the long-tail of music. This allows streaming services to create richer playlists featuring a wider range of artists and exposes fans to different styles of music and artists that they may not have discovered on their own. In addition, Sonic Style data will help human music curators and algorithms filter outliers from playlists and recommendations. For example, for an eclectic artist such as The Clash, one could ensure that an Old School Punk playlist contained only tracks truly of that style such as "Career Opportunities," and excluded others such as the funky "Magnificent Seven," based on that track's actual Sonic Style of "New Wave Dance.”
As popularity of smart speakers continue to grow, device makers and streaming services require more descriptive information about music to deliver better playlists while using voice commands. With the new layer of track-level insight, Gracenote Sonic Style enables a more natural interaction with smart speakers and voice assistants by providing data to understand descriptive commands like "play me tracks with a Tropical House vibe from my favorite artists" or "play some G-Funk style tracks."
As part of Gracenote's core Global Music Data, Sonic Style complements the company's editorially assigned descriptors, including artist genre, era, and origin, as well as other machine learning descriptors such as tempo and mood, to provide a powerful combination of quality and coverage to drive entirely new playlisting and discovery experiences. Gracenote has nearly 450 Sonic Style descriptor values and a weighted system to accurately describe the rich, multi-value "style profile" of each recording.
Gracenote Global Music Data is the global database of record for the music industry, offering the most comprehensive collection of worldwide music data available today. It enables streaming music services, voice-powered virtual assistants and online media companies to better manage searches across a sea of artist releases, collaborations, remixes and live recordings. Gracenote Global Music Data also links musical artists and songs across linear TV, VOD catalogs and popular streaming music services, enabling the discovery of new artists and music across cable and satellite TV programs.
www.gracenote.com
