SDLGASDec 2, 2020

Sequence Generation using Deep Recurrent Networks and Embeddings: A study case in music

arXiv:2012.01231v11 citations
AI Analysis

This research addresses the problem of automatic music composition for musicians and AI researchers, representing an incremental step in applying existing methods to a specific domain.

This paper explores the use of deep recurrent networks and embeddings for automatic music composition, evaluating various memory mechanisms. It incorporates music theory concepts like transposition and data transformations to enhance the semantic meaning and quality of generated melodies, using quantitative metrics to assess tonality.

Automatic generation of sequences has been a highly explored field in the last years. In particular, natural language processing and automatic music composition have gained importance due to the recent advances in machine learning and Neural Networks with intrinsic memory mechanisms such as Recurrent Neural Networks. This paper evaluates different types of memory mechanisms (memory cells) and analyses their performance in the field of music composition. The proposed approach considers music theory concepts such as transposition, and uses data transformations (embeddings) to introduce semantic meaning and improve the quality of the generated melodies. A set of quantitative metrics is presented to evaluate the performance of the proposed architecture automatically, measuring the tonality of the musical compositions.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes