@article{seeingisnthearingbenchmarkingvisionlangu,
  title = {Seeing isn't Hearing: Benchmarking Vision Language Models at Interpreting Spectrograms},
  author = {Tyler Loakman and Joseph James and Chenghua Lin},
  year = {2025},
  eprint = {2511.13225},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.13225},
}