@misc{arxiv_2609_12663,
  title = {What Did the MLLM Hear? Token-Level Spectro-Temporal Grounding for Audio MLLM Explainability},
  author = {{Lucia Cascone} and {Valeria Fraenza} and {Michele Nappi} and {Fabio Narducci} and {Benedetto Simone}},
  eprint = {2609.12663},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.12663}
}