DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
Authors:
- Ke-Han LuKLKe-Han Lu
- Zhehuai ChenZCZhehuai Chen
- Szu-Wei FuSFSzu-Wei Fu
- Chao-Han Huck YangCYChao-Han Huck Yang
- Sung-Feng HuangSHSung-Feng Huang
- Chih-Kai YangCYChih-Kai Yang
- Chee-En YuCYChee-En Yu
- Chun-Wei ChenCCChun-Wei Chen
- Wei-Chih ChenWCWei-Chih Chen
- Chien-Yu HuangCHChien-Yu Huang
- Yi-Cheng LinYLYi-Cheng Lin
- Yu-Xiang LinYLYu-Xiang Lin
Preprint