构建公开病理语音评估基准，统一方法对比标准。
PathBench: Speech Intelligibility Benchmark for Automatic Pathological Speech Assessment
- 整合六大数据集，设计三类评估协议统一测试标准。
- 提出Dual-ASR Articulatory Precision，参考无模型相关性最高。
- 适合语音病理评估、智能诊断研究者使用。
自动语音可懂度评估对监测语音障碍及治疗效果至关重要。然而现有方法难以比较：研究分散于私有数据集且协议不一。我们提出PathBench，一个基于公开数据集的统一病理语音评估基准。在三种协议（匹配内容、扩展、完整）下，对比无参考、参考文本与参考音频三类方法，分别模拟语言学家（控制刺激）与机器学习专家（最大化数据）的分析思路。建立六个数据集的基准线，支持未来方法系统评估，并引入双声道ASR发音精度（DArtP），在无参考方法中达到最高平均相关性。
原文摘要 · Abstract (English)
Automatic speech intelligibility assessment is crucial for monitoring speech disorders and therapy efficacy. However, existing methods are difficult to compare: research is fragmented across private datasets with inconsistent protocols. We introduce PathBench, a unified benchmark for pathological speech assessment using public datasets. We compare reference-free, reference-text, and reference-audio methods across three protocols (Matched Content, Extended, and Full) representing how a linguist (controlled stimuli) versus machine learning specialist (maximum data) would approach the same data. We establish benchmark baselines across six datasets, enabling systematic evaluation of future methodological advances, and introduce Dual-ASR Articulatory Precision (DArtP), achieving the highest average correlation among reference-free methods.
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。