@inproceedings{zhang-etal-2026-beyond-transcription, title = "Beyond Transcription: Unified Audio Schema for Perception-Aware {A}udio{LLM}s", author = "Zhang, Linhao and Song, Yuhan and Liu, Aiwei and Wu, Chuhan and Zhang, Sijun and Jia, Wei and Liu, Yuan and Wang, Houfeng and Xiao, Zhou", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.967/", pages = "19375--19390", ISBN = "979-8-89176-395-1" }