Large Vision and Multimodal Models | Views : 0 下载量: 55 CSCD: 0
  • Export

  • Share

  • Collection

  • Album

    • Information disentanglement-based self-supervised learning speech pretrained large model

    • In the field of speech interaction, experts have proposed a pre trained large model based on speech information decoupling strategy, which effectively improves the model's ability to parse and reconstruct speech information, providing a new research perspective and practical tool for speech interaction large models.
    • Vol. 30, Issue 5, Pages: 1272-1285(2025)   

      Received:31 December 2024

      Revised:23 February 2025

      Published:16 May 2025

    • DOI: 10.11834/jig.240607     

    移动端阅览

  • Wang Longbiao, Jiang Yu, Wang Tianrui, Wang Xiaobao, Dang Jianwu. 2025. Information disentanglement-based self-supervised learning speech pretrained large model. Journal of Image and Graphics, 30(5):1272-1285 DOI: 10.11834/jig.240607.
  •  
  •  
Alert me when the article has been cited
提交

相关作者

Wang Longbiao 天津大学智能与计算学部认知计算与应用重点实验室
Jiang Yu 天津大学智能与计算学部认知计算与应用重点实验室
Wang Tianrui 天津大学智能与计算学部认知计算与应用重点实验室
Wang Xiaobao 天津大学智能与计算学部认知计算与应用重点实验室
Dang Jianwu 中国科学院深圳先进技术研究院
Zheng Hu 北方民族大学计算机科学与工程学院
Yan Hao 北方民族大学计算机科学与工程学院
Bai Jing 北方民族大学计算机科学与工程学院;国家民委图像图形智能处理实验室

相关机构

School of Computer Science and Engineering, North Minzu University
The Key Laboratory of Images and Graphics Intelligent Processing of State Ethnic Affairs Commission
Platform Product Department,China Mobile(Suzhou) Software Technology Co., Ltd.
School of Computer Science, Peking University
College of Electrical and Information Engineering, Hunan University
0