作者位次 #7/13ACL 2026Poster· Natural Language Processing
U ni S onate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions
Chunyu Qiang · Xiaopeng Wang · Kang Yin · Yuzhe Liang · Yuxin Guo · Teng Ma · Ziyu Zhang · Tianrui Wang · Cheng Gong · Yushen Chen · Ruibo Fu · Longbiao Wang · Jianwu Dang
摘要
Generative audio modeling has largely been fragmented into specialized tasks, text-to-speech (TTS), text-to-music (TTM), and text-to-audio (TTA), each operating under heterogeneous control paradigms. Unifying these modalities remains a fundamental challenge due to the intrinsic dissonance between...