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

Abstract

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.

References in corpus (6)

• Deep Learning in Neural Networks: An Overview
• Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
• Optical Music Recognition with Convolutional Sequence-to-Sequence Models
• Modeling Musical Context with Word2vec
• Embeddings as representation for symbolic music
• Cross entropy as objective function for music generative models

Cited by in corpus (1)

• A framework to compare music generative models using automatic evaluation metrics extended to rhythm