@inproceedings{feng-etal-2026-childvox, title = "{C}hild{V}ox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood", author = "Feng, Tiantian and Xu, Anfeng and Shi, Xuan and Kommineni, Aditya and Siam, Shakhrul Iman and Micheletti, Megan and Shi, Zhonghao and Tager-Flusberg, Helen and Zhang, Mi and Perry, Lynn K and Lord, Catherine and Messinger, Daniel and Narayanan, Shrikanth", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.emnlp-main.1756/", pages = "40054--40072", ISBN = "979-8-89176-459-0" }