Embeddings as representation for symbolic music
This work addresses the need for better music representations for AI in music, but it is incremental as it applies existing NLP embedding techniques to music data.
The paper tackles the problem of representing symbolic music with meaningful embeddings to improve computer music tasks like melody and harmony generation, and finds that the model can capture useful musical patterns as visualized through t-SNE projections.
A representation technique that allows encoding music in a way that contains musical meaning would improve the results of any model trained for computer music tasks like generation of melodies and harmonies of better quality. The field of natural language processing has done a lot of work in finding a way to capture the semantic meaning of words and sentences, and word embeddings have successfully shown the capabilities for such a task. In this paper, we experiment with embeddings to represent musical notes from 3 different variations of a dataset and analyze if the model can capture useful musical patterns. To do this, the resulting embeddings are visualized in projections using the t-SNE technique.