English
Russian
French
Spanish
German
Japanese
korean
PortugueseBlog
Apr 05, 2026
The Hidden Audio Bias Inside Audio-Visual Speech Recognition
Shapley analysis reveals why AVSR models keep trusting corrupted audio, exposing a hidden bias in multimodal speech recognition.
Source: HackerNoon →Shapley analysis reveals why AVSR models keep trusting corrupted audio, exposing a hidden bias in multimodal speech recognition.
Source: HackerNoon →
