Distributed Vector Representations of Folksong Motifs
This work addresses the study of folksong variation for musicology researchers, but it is incremental as it applies an existing method to a new domain.
The authors tackled the problem of representing folksong motifs as distributed vectors using a skip-gram word2vec model with negative sampling, resulting in embeddings that capture complex contextual features and enable melodic similarity comparisons, as demonstrated through a new evaluation method on the Essen Folksong collection.
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.