DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model With Self-Generated Cross-Modal Alignment

IEEE Transactions on Audio Speech and Language Processing 2026

View at publisher
Authors: K C Lu, Zhehuai Chen, Szu‐Wei Fu, Chao-Han Huck Yang, Sung-Feng Huang, C. C. Yang, Chia-Mu Yu, Chun‐Wei Chen, Weiyou Chen, Chien-yu Huang, Yi‐Cheng Lin, Yuxiang Lin
+16 more Chi-An Fu, Chun-Yi Kuan, Wenze Ren, Xuanjun Chen, Wei-Ping Huang, En-Pei Hu, T. W. Lin, Yuan-Kuei Wu, Kuan-Po Huang, Hsiao-Ying Huang, Huang-Cheng Chou, Kai-Wei Chang, Cheng-Han Chiang, Boris Ginsburg, Yu-Chiang Frank Wang, Hung-yi Lee
DOI: 10.1109/taslpro.2026.3675792
Cited by: 6
References: 72

Fields of Study & Subjects

Speech Recognition and Synthesis Music and Audio Processing Speech and Audio Processing

Publication details

Journal / source
IEEE Transactions on Audio Speech and Language Processing
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Volume
34
Pages
2062–2076
Publication date
1 January 2026