dc.rights.license | CC-BY-NC-ND | |
dc.contributor.advisor | Gauthier, David | |
dc.contributor.author | Skalski, Szymon | |
dc.date.accessioned | 2024-02-15T14:57:04Z | |
dc.date.available | 2024-02-15T14:57:04Z | |
dc.date.issued | 2024 | |
dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/45997 | |
dc.description.sponsorship | Utrecht University | |
dc.language.iso | EN | |
dc.subject | This thesis proposed a post-genre recommendation system focused only on the sonic characteristics of songs to create music recommendations. The study utilized a selection of spectral and temporal features extracted from audio files, employing the GTZAN dataset. The relevance of the features was assessed, to determine which ones provided the most accurate representation of audio content. This study prioritized the audio content as a key factor in the creation of music recommendations. | |
dc.title | What you hear is what you get: Post-genre, feature-based music recommendation system | |
dc.type.content | Master Thesis | |
dc.rights.accessrights | Open Access | |
dc.subject.keywords | audio features; music recommendation system; | |
dc.subject.courseuu | Applied Data Science | |
dc.thesis.id | 21629 | |