At the moment, customers can hearken to music and uncover new artists, songs or albums on a wide range of music streaming platforms, together with Spotify, Apple Music, Amazon Music Limitless and extra. Many builders have been attempting to create instruments that would enhance these providers, comparable to music suggestion programs that recommend new songs or playlists to customers based mostly on their preferences and on music they listened to previously.
Researchers at Seoul Nationwide College just lately created an interactive knowledge visualization instrument that would improve each present and rising music streaming providers. This instrument, referred to as Music Circles, can signify songs as distinctive vectors after which calculate similarities between completely different vectors to group comparable songs into clusters.
“As music lovers with completely different tastes, we got here collectively for a undertaking that may discover novel methods of visually representing and grouping summary music knowledge,” Seokgi Kim, Jihye Park, Kihong Seong, Namwoo Cho, Junho Min and Hwajung Hong, the researchers who carried out the examine, informed TechXplore through electronic mail. “We needed to diverge from conventional methods of discovering comparable music by way of genres, artists, and many others. The core concept was to signify songs with numbers by assigning embeddings based mostly on numerical audio characteristic values, comparable to acousticness and danceability.”
The first goal of the examine carried out by Kim and his colleagues was to assist customers to seek for music they could like and discover music streaming catalogs in methods which can be extra intuitive and interesting. Music Circles, the system they created, calculates the similarity between completely different songs by representing them as vectors, to make looking for out personalised music extra entertaining.
“The sequence of interactions and visualizations in our undertaking makes knowledge exploration more practical and environment friendly,” the researchers defined. “Our visualizations, which resemble circles (therefore the title), present fascinating info (e.g., tendencies in music) based mostly on relationships between audio options of songs.”
Primarily, Music Circles arranges songs as completely different cluster visualizations that match the music style of particular person customers. To entry tune clusters aligned with their musical preferences, customers merely have to take a survey about their tune preferences. Music Circles makes use of the information collected by way of this survey to generate visualizations of tune clusters aligned with a person’s preferences.
“We stray away from the normal music suggestion outlook (album covers + listing of songs) and supply visualizations of traits of sure clusters,” the researchers stated.
“With applicable annotations and punctiliously chosen designs, we really feel that the undertaking is each pleasant and informative. Whereas visualization in music suggestion is scarce usually, our undertaking highlights the truth that knowledge visualization could make looking/searching for music extra pleasant and efficient.”
In distinction with different music suggestion programs developed previously, Music Circles locations versatile artists who produce a spread of various songs into a couple of cluster. For example, if Ed Sheeran’s songs have been to be advisable to customers solely based mostly on what artists they listened to previously, his songs would solely be advisable to a restricted viewers. Music Circles, alternatively, locations completely different songs by Ed Sheeran in several clusters, based mostly on their distinctive attributes and traits, thus recommending them to a wider vary of customers.
Sooner or later, the system could possibly be used to enhance music streaming providers; as an example, permitting customers to achieve a greater understanding of audio options, uncover new songs they could like, view present music tendencies and uncover what music cluster they belong to. The Music Circles framework is now obtainable on-line and will be accessed at: https://musiccircles.netlify.app/ .
“As knowledge scientists, we wish to make the most of underrated attributes of songs comparable to producers, lyricists (individuals who may be extra associated to the music than the precise artist) and supply distinctive music suggestions that differs from streaming powerhouses like Spotify and Apple Music,” the researchers stated. “We additionally wish to make the undertaking scalable to massive knowledge. We want to show a bigger set of music in a extra environment friendly method to supply our undertaking to extra music lovers.”
Apple Music’s new Replay characteristic will present your most-played music of 2019
Music-Circles: can music be represented with numbers? arXiv: 2102.13350 [cs.HC]. arxiv.org/abs/2102.13350
© 2021 Science X Community
Music Circles: An interactive knowledge visualization instrument that helps customers uncover new music (2021, March 16)
retrieved 17 March 2021
This doc is topic to copyright. Other than any truthful dealing for the aim of personal examine or analysis, no
half could also be reproduced with out the written permission. The content material is supplied for info functions solely.