新模型统一语音和歌声生成

报道来源 [3]

1. arXiv cs.AI TIER_1 English(EN) · Ziyu Zhang, Chunyu Qiang, Xiaopeng Wang, Yuxin Guo, Kang Yin, Wenjie Tian, Jingbin Hu, Tianlun Zuo, Zhao Guo, Teng Ma, Yuzhe Liang, Chen Zhang, Lei Xie · 2026-06-08 04:00

   迈向统一的歌曲生成与歌声转换伴奏共生

   arXiv:2606.07015v1 Announce Type: cross Abstract: While song generation and singing voice conversion (SVC) have evolved significantly, they have long been developed isolated: the former lacks zero-shot speaker cloning, while the latter overlooks vocal-accompaniment synergy. To br…

2. arXiv cs.AI TIER_1 English(EN) · Junjie Zheng, Huixin Xue, Shihong Ren, Chaofan Ding, Hao Liu, Zihao Chen · 2026-06-06 04:00

   UniVoice：统一的语音和歌声生成模型

   arXiv:2606.05852v1 Announce Type: cross Abstract: Text-to-speech (TTS) and singing voice synthesis (SVS) both aim to generate human vocal audio from symbolic inputs, but they impose different requirements on the generation process. Speech generation relies on flexible, language-d…

3. arXiv cs.AI TIER_1 English(EN) · Lei Xie · 2026-06-05 07:59

   迈向统一的歌曲生成与歌声转换，并伴随伴奏的协同生成

   While song generation and singing voice conversion (SVC) have evolved significantly, they have long been developed isolated: the former lacks zero-shot speaker cloning, while the latter overlooks vocal-accompaniment synergy. To bridge this gap, we propose UniSinger, the first end…