一作ACL 2026Findings· Findings of ACL
Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses
Sungnyun Kim · Kangwook Jang · Sungwoo Cho · Joon Son Chung · Hoi-Rin Kim · Se-Young Yun
摘要
This paper introduces a new paradigm for generative error correction (GER) framework in audio-visual speech recognition (AVSR) that reasons over modality-specific evidences directly in the language space. Our framework, DualHyp , empowers a large language model (LLM) to compose independent N -bes...