Modeling Musical Context with Word2vec

Abstract

We present a semantic vector space model for capturing complex polyphonic musical context. A word2vec model based on a skip-gram representation with negative sampling was used to model slices of music from a dataset of Beethoven's piano sonatas. A visualization of the reduced vector space using t-distributed stochastic neighbor embedding shows that the resulting embedded vector space captures tonal relationships, even without any explicit information about the musical contents of the slices. Secondly, an excerpt of the Moonlight Sonata from Beethoven was altered by replacing slices based on context similarity. The resulting music shows that the selected slice based on similar word2vec context also has a relatively short tonal distance from the original slice.

Proceedings of the First International Conference on Deep Learning and Music, Anchorage, US, May, 2017 (arXiv:1706.08675v1 [cs.NE])

References in corpus (4)

• From Frequency to Meaning: Vector Space Models of Semantics
• Exploiting Similarities among Languages for Machine Translation
• word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method
• Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription

Cited by in corpus (7)

• Melody Generation using an Interactive Evolutionary Algorithm
• MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
• Embeddings as representation for symbolic music
• An Attentional Neural Network Architecture for Folk Song Classification
• Distributed Vector Representations of Folksong Motifs
• Sequence Generation using Deep Recurrent Networks and Embeddings: A study case in music
• Self-Supervised Learning of Context-Aware Pitch Prosody Representations