Visual Information Matters for ASR Error Correction

16 March 2023

Papers citing "Visual Information Matters for ASR Error Correction"

2 / 2 papers shown

Title
VHASR: A Multimodal Speech Recognition System With Vision Hotwords Jiliang Hu Zuchao Li Ping Wang Haojun Ai Lefei Zhang Hai Zhao 16 1 0 01 Oct 2024
Robust Audiovisual Speech Recognition Models with Mixture-of-Experts Yihan Wu Yifan Peng Yichen Lu Xuankai Chang Ruihua Song Shinji Watanabe 44 10 0 19 Sep 2024