AI RESEARCH
Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades
arXiv CS.CL
•
ArXi:2605.17443v1 Announce Type: new We analyze how automatic speech recognition (ASR) errors propagate through ASR-LLM cascades in Korean spoken question answering (SQA), focusing on downstream semantic failures that conventional ASR metrics cannot fully capture. Our analysis shows that the relative downstream degradation caused by ASR errors is consistent across LLMs with different absolute performance, suggesting that cascade degradation largely tracks ASR-stage information loss.