WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue
This addresses a safety gap in ASR evaluation for clinical dialogue, providing a scalable automated framework, though it is incremental as it builds on existing LLM and optimization methods.
The paper tackled the problem that standard Word Error Rate (WER) metrics poorly correlate with clinical impact in ASR for patient dialogues, and introduced an LLM-as-a-Judge optimized with GEPA that achieved 90% accuracy and a Cohen's κ of 0.816 in replicating expert assessments.
As Automatic Speech Recognition (ASR) is increasingly deployed in clinical dialogue, standard evaluations still rely heavily on Word Error Rate (WER). This paper challenges that standard, investigating whether WER or other common metrics correlate with the clinical impact of transcription errors. We establish a gold-standard benchmark by having expert clinicians compare ground-truth utterances to their ASR-generated counterparts, labeling the clinical impact of any discrepancies found in two distinct doctor-patient dialogue datasets. Our analysis reveals that WER and a comprehensive suite of existing metrics correlate poorly with the clinician-assigned risk labels (No, Minimal, or Significant Impact). To bridge this evaluation gap, we introduce an LLM-as-a-Judge, programmatically optimized using GEPA to replicate expert clinical assessment. The optimized judge (Gemini-2.5-Pro) achieves human-comparable performance, obtaining 90% accuracy and a strong Cohen's $κ$ of 0.816. This work provides a validated, automated framework for moving ASR evaluation beyond simple textual fidelity to a necessary, scalable assessment of safety in clinical dialogue.