Article

Hyperbolic Embeddings for Music Taxonomy

2020-10-05

Abstract excerpt

<p>Musical genres are inherently ambiguous and difficult to define. Even more so is the task of establishing how genres relate to one another. Yet, genre is perhaps the most common and effective way of describing musical experience. The number of possible genre classifications (e.g. Spotify has over 4000 genre tags, LastFM over 500,000 tags) has made the idea of manually creating music taxonomies obsolete. We prop...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 81816254-a10f-576b-8834-3895265defd6
DOI: 10.31234/osf.io/e2qyd

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 11 closest

Hyperbolic Embeddings for Music TaxonomyDOI 10.31234/osf.io/e2qydRead

A General-Purpose Sound Taxonomy for the Classification of Heterogeneous Sound CollectionsSemantic proximity Read

Intrinsic Thematic Separability in Sentence-Transformer Embeddings: A Controlled Geometric Study from Synthetic to Real-World TextSemantic proximity Read

Pitches that Wire Together Fire Together: Scale Degree Associations Across Time Predict Melodic ExpectationsSemantic proximity Read

Improvised music follows human language quantitative properties to optimize music processingSemantic proximity Read

Deep audio embeddings for vocalisation clusteringSemantic proximity Read

CompoNet: Toward Incorporating Human Perspective in Automatic Music Generation Using Deep LearningSemantic proximity Read

The latent geometry of dream contentSemantic proximity Read

The Exceptions and the Rules in global musical diversitySemantic proximity Read

Diurnal fluctuations in musical preferenceSemantic proximity Read

A Deep Learning Framework for Emotion Recognitionin Music Using Multimodal Data FusionSemantic proximity Read

Small-integer ratios predominate throughout the world's musical scalesSemantic proximity Read