arXivYuhan Song, Linhao Zhang, Aiwei Liu, Chuhan Wu, Sijun Zhang, Wei Jia, Yuan Liu, Houfeng Wang, Xiao ZhouFri, May 29, 2026, 9:36 AM PDT
score 14.7
Single tokenizer handles speech and general audio without losing quality
Original: UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perception
Source: arxiv.org ↗
Writing ELI5 summary…