Deep Segment Hash Learning for Music Generation
This addresses music generation for creative applications, but it appears incremental as it builds on existing segment concatenation and hash learning methods.
The paper tackles music generation by proposing Deep Segment Hash Learning (DSHL), which uses deep recurrent neural networks and ranking-based hash learning to assign hash codes to music segments for retrieval and concatenation, resulting in music that is described as original and enjoyable.
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.