Jinlong Zhu, Keigo Sakurai, Ren Togo, Takahiro Ogawa, M. Haseyama

2026ITE Transactions on Media Technology and Applications

DOI: 10.3169/mta.14.110

Abstract

We propose a novel text-controllable polyphonic symbolic music generation method based on diffusion models. Symbolic music generation has garnered significant attention due to its flexibility and seamless integration with Digital Audio Workstations (DAWs), as it enables the generation of MIDI files, facilitating easier modification compared to waveform mu- sic. Although existing techniques enable control through chords or other metadata, few

Citation format

ZHU, Jinlong, et al. [Paper] TPSMG: Text-controllable polyphonic symbolic music generation. ITE Transactions on Media Technology and Applications, 2026.