Your Location：
Home >
Browse articles >
Multi-talker audio–visual speech recognition towards diverse scenarios&
Regular Papers | Updated：2026-01-07

    • Multi-talker audio–visual speech recognition towards diverse scenarios&

      Enhanced Publication
    • 面向多样化场景的多说话者音频─视觉语音识别
    • “In the field of audio-visual speech recognition, a new end-to-end framework has been proposed. Expert xx established the speaker-number-aware mixture-of-experts mechanism and cross-modal realignment module, which provides solutions to solve the problems of speaker number and modal misalignment in AVSR tasks.”
    • Frontiers of Information Technology & Electronic Engineering   Vol. 26, Issue 11, Pages: 2310-2323(2025)

    • DOI：10.1631/FITEE.2500411    

      CLC： TP18

    • Received：13 June 2025，

      Revised：2025-11-02，

      Published Online：08 December 2025，

      Published：2025-11

    Scan QR Code

  • Yuxiao LIN, Tao JIN, Xize CHENG, et al. Multi-talker audio–visual speech recognition towards diverse scenarios&[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(11): 2310-2323. DOI： 10.1631/FITEE.2500411.

  •  
  •  

0

Views

0

Downloads

0

CSCD

PlumX

>
Alert me when the article has been cited
Submit
Tools
Download
Export Citation
Share
Add to favorites
Add to my album

Related Articles

No data

Related Author

No data

Related Institution

No data
0