作者位次 #5/6ACL 2026Poster· Natural Language Processing
Listening Like Humans: Semantics-Guided Noise-Robust Multimodal Speech Recognition
Yan Fang · Jun Chen · Yian Yao · Shuxin Zhong · Min Sun · Kaishun Wu
摘要
Severe acoustic degradation is often caused by overlapping noise, disfluencies, and environmental distortions. This phenomenon results in the dissolution of linguistic structures and the generation of unreliable ASR outputs. Inspired by human speech comprehension, we propose Speech-MLM, a novel m...