Structure-informed Positional Encoding for Music Generation
Music generated by deep learning methods often suffers from a lack of coherence and long-term organization. Yet, multi-scale hierarchical structure is a distinctive feature of music signals. To leverage this information, we propose a structure-informed positional encoding framework for music generation with Transformers. We design three variants in terms of absolute, relative and non-stationary positional information. We comprehensively test them on two symbolic music generation tasks: next-timestep prediction and accompaniment generation. As a comparison, we choose multiple baselines from the literature and demonstrate the merits of our methods using several musically-motivated evaluation metrics. In particular, our methods improve the melodic and structural consistency of the generated pieces.
Code (0)
등록된 구현이 없습니다.
Tasks
Music GenerationSimilar Papers 제목 키워드 기반
F-StrIPE: Fast Structure-Informed Positional Encoding for Symbolic Music Generation
While music remains a challenging domain for generative models like Transformers, recent progress has been made by exploiting suitable musically-informed priors. One technique to leverage information about musical struct…
Music GenerationOf All StrIPEs: Investigating Structure-informed Positional Encoding for Efficient Music Generation
While music remains a challenging domain for generative models like Transformers, a two-pronged approach has recently proved successful: inserting musically-relevant structural information into the positional encoding (P…
AllMusic GenerationTemporal SequencesDiscovering "Words" in Music: Unsupervised Learning of Compositional Sparse Code for Symbolic Music
This paper presents an unsupervised machine learning algorithm that identifies recurring patterns -- referred to as ``music-words'' -- from symbolic music data. These patterns are fundamental to musical structure and ref…
Music GenerationStyle TransferRelative Positional Encoding for Transformers with Linear Complexity
Recent advances in Transformer models allow for unprecedented sequence lengths, due to linear space and time complexity. In the meantime, relative positional encoding (RPE) was proposed as beneficial for classical Transf…
Gaussian ProcessesImage ClassificationMusic GenerationText ClassificationThe Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation
With recent breakthroughs in artificial neural networks, deep generative models have become one of the leading techniques for computational creativity. Despite very promising progress on image and short sequence generati…
Music Generation