تقرير
Uncovering audio patterns in music with Nonnegative Tucker Decomposition for structural segmentation
العنوان: | Uncovering audio patterns in music with Nonnegative Tucker Decomposition for structural segmentation |
---|---|
المؤلفون: | Marmoret, Axel, Cohen, Jérémy E., Bertin, Nancy, Bimbot, Frédéric |
المصدر: | 21st International Society for Music Information Retrieval Conference (ISMIR), Montr\'eal, Canada, 2020, 788-794 |
سنة النشر: | 2021 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Sound, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Audio and Speech Processing, H.5.5 |
الوصف: | Recent work has proposed the use of tensor decomposition to model repetitions and to separate tracks in loop-based electronic music. The present work investigates further on the ability of Nonnegative Tucker Decompositon (NTD) to uncover musical patterns and structure in pop songs in their audio form. Exploiting the fact that NTD tends to express the content of bars as linear combinations of a few patterns, we illustrate the ability of the decomposition to capture and single out repeated motifs in the corresponding compressed space, which can be interpreted from a musical viewpoint. The resulting features also turn out to be efficient for structural segmentation, leading to experimental results on the RWC Pop data set which are potentially challenging state-of-the-art approaches that rely on extensive example-based learning schemes. Comment: 7 pages, 6 figures; Code and experiments details available at https://gitlab.inria.fr/amarmore/musicntd/-/tree/0.1.0; Experiments details available at https://ax-le.github.io/resources/ISMIR2020/Notebooks_mainpage.html |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2104.08580 |
رقم الأكسشن: | edsarx.2104.08580 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |