SOURCE-LINKED INTELLIGENCE

Attention-Guided Reliability Scaling for Contrastive Decoding in Robust Audio-Visual Speech Recognition

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Large language model (LLM)-based audio-visual speech recognition (AVSR) systems are robust under noise. Contrastive decoding (CD), originally introduced to stabilize LLM generation by contrasting a weaker model against a stronger one at inference time, adjusts predictions without additional training. In this work, we apply CD to AVSR by contrasting audio-only conditioning with full audio-visual conditioning within the same underlying model. However, using a fixed contrastive strength introduces a trade-off across noise levels: stronger intervention helps under severe noise but may over-correct

Read original source ↗ Open in workspace

recordType

paper

region

Global