@misc{arxiv_2611_00685v1,
  title = {Text-to-music Generation via Structured Captions AND Interpretable Evaluation},
  author = {{Junkai Wu} and {Zhepei Wang} and {Ge Zhu} and {Sarah Hye-yeon Lee} and {Mari Ostendorf} and {Nicholas J. Bryan}},
  eprint = {2611.00685v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.00685v1}
}