提出可解释的无参考语音清晰度评估方法，提升病理语音评价效率。
Towards explainable reference-free speech intelligibility evaluation of people with pathological speech
- 基于ASR不一致性构建无参考评估指标，无需人工转录。
- 在荷、西、英三语病理语音上与专家评分高度相关，性能媲美甚至超过基线WER。
- 适合临床评估和自动化语音研究，尤其关注可解释性场景。
客观评估语音以反映沟通能力的真实变化，对临床决策和可重复研究至关重要。现有客观评估方法，尤其是依赖参考文本的方法，常因缺乏可解释性及需大量人工转录而受限。为此，本文提出一种无参考、可解释的ASR不一致性评分（ASR Inconsistency Score）。我们在荷兰语、西班牙语和英语的病理语音数据上评估该方法，并与基于参考文本的词错误率（WER）基准进行对比。结果表明，该评分与专家感知评分具有高相关性，表现接近甚至在某些情况下超越标准参考基线WER。
原文摘要 · Abstract (English)
Objective assessment of speech that reflects meaningful changes in communication is crucial for clinical decision making and reproducible research. While existing objective assessments, particularly reference-based approaches, can capture intelligibility changes, they are often hindered by lack of explainability and the need for labor-intensive manual transcriptions. To address these issues, this work proposes the reference-free, explainable ASR Inconsistency Score. We evaluate this method on pathological speech in Dutch, Spanish and English, and compare its performance to a reference-based Word Error Rate (WER) baseline. Our results demonstrate that the ASR Inconsistency Score achieves a high correlation with expert perceptual ratings, with performance closely matching, and in one case exceeding, a standard reference-based Word Error Rate (WER) baseline.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。