DashengTokenizer: One layer is enough for unified audio understanding and generation

Open Webpage

Heinrich Dinkel, Xingwei Sun, Gang Li, Jiahao Mei, Yadong Niu, Jizhong Liu, Xiyang Li, Yifan Liao, Jiahao Zhou, Junbo Zhang, Jian Luan

Published: 2026, Last Modified: 06 May 2026CoRR 2026EveryoneRevisionsBibTeXCC BY-SA 4.0