Published August 20, 2018 | Version v1
Conference paper Open

Deep Segment Hash Learning for Music Generation

Description

Music generation research has grown in popularity over the past decade, thanks to the deep learning revolution that has redefined the landscape of artificial intelligence. In this paper, we propose a novel approach to music generation inspired by musical segment concatenation methods and hash learning algorithms. Given a segment of music, we use a deep recurrent neural network and ranking-based hash learning to assign a forward hash code to the segment to retrieve candidate segments for continuation with matching backward hash codes. The proposed method is thus called Deep Segment Hash Learning (DSHL). To the best of our knowledge, DSHL is the first end-to-end segment hash learning method for music generation, and the first to use pair-wise training with segments of music. We demonstrate that this method is capable of generating music which is both original and enjoyable, and that DSHL offers a promising new direction for music generation research.

Files

Joslyn.pdf

Files (501.1 kB)

Name Size Download all
md5:35409f027a434dd5f4d4e5b8511f1f42
501.1 kB Preview Download