SinTra: Learning an inspiration model from a single multi-track music segment
This addresses the challenge of music generation with minimal training data for creators and researchers, though it is incremental as it builds on existing transformer-based methods.
The authors tackled the problem of generating coherent and variable multi-instrument polyphonic music from a single training segment, achieving results that outperform Music Transformer in learning from limited data and suppressing fragmented notes.
In this paper, we propose SinTra, an auto-regressive sequential generative model that can learn from a single multi-track music segment, to generate coherent, aesthetic, and variable polyphonic music of multi-instruments with an arbitrary length of bar. For this task, to ensure the relevance of generated samples and training music, we present a novel pitch-group representation. SinTra, consisting of a pyramid of Transformer-XL with a multi-scale training strategy, can learn both the musical structure and the relative positional relationship between notes of the single training music segment. Additionally, for maintaining the inter-track correlation, we use the convolution operation to process multi-track music, and when decoding, the tracks are independent to each other to prevent interference. We evaluate SinTra with both subjective study and objective metrics. The comparison results show that our framework can learn information from a single music segment more sufficiently than Music Transformer. Also the comparison between SinTra and its variant, i.e., the single-stage SinTra with the first stage only, shows that the pyramid structure can effectively suppress overly-fragmented notes.