Distributed Vector Representations of Folksong Motifs
From MaRDI portal
Publication:5237283
DOI10.1007/978-3-030-21392-3_26zbMATH Open1456.00057arXiv1903.08756OpenAlexW2964053001MaRDI QIDQ5237283FDOQ5237283
Authors: Aitor Arronte Alvarez, Francisco Gómez-Martín
Publication date: 17 October 2019
Published in: Mathematics and Computation in Music (Search for Journal in Brave)
Abstract: This article presents a distributed vector representation model for learning folksong motifs. A skip-gram version of word2vec with negative sampling is used to represent high quality embeddings. Motifs from the Essen Folksong collection are compared based on their cosine similarity. A new evaluation method for testing the quality of the embeddings based on a melodic similarity task is presented to show how the vector space can represent complex contextual features, and how it can be utilized for the study of folksong variation.
Full work available at URL: https://arxiv.org/abs/1903.08756
Recommendations
- Contrast pattern mining in folk music analysis
- Comparing computational approaches to rhythmic and melodic similarity in folksong research
- On pitch and chord stability in folk song variation retrieval
- Computing melodic templates in oral music traditions
- A mathematical study of note association paradigms in different folk music cultures
- Sparse representations of polyphonic music
- Modelling pattern interestingness in comparative music corpus analysis
Neural networks for/in biological studies, artificial life and related topics (92B20) Mathematics and music (00A65)
Cites Work
Cited In (3)
Uses Software
This page was built for publication: Distributed Vector Representations of Folksong Motifs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5237283)