1
FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing
无需训练的时间感知解耦注意力机制，实现高精度音频编辑，被Interspeech 2026收录。
arXiv:2606.15186v1 Announce Type: cross Abstract: Text-to-audio (TTA) generation has made significant strides, yet achieving precise and consistent au…