通过多粒度语音分析，提升跨语言帕金森病诊断准确率
Cross-Lingual Multi-Granularity Framework for Interpretable Parkinson's Disease Diagnosis from Speech
- 按音素、音节、词三级提取语音特征，实现细粒度分析
- 音素级分析达到93.78%的AUROC和92.17%准确率
- 识别出临床常用发音特征，结果可解释性强
帕金森病影响全球超1000万人，高达89%患者存在言语障碍。现有基于语音的检测系统通常分析整句，可能忽略特定语音成分的诊断价值。本文提出一种跨语言多粒度分析框架，通过自动化流程从录音中提取时间对齐的音素、音节和词。在意大利语、西班牙语和英语数据集上，采用双向LSTM结合多头注意力模型，在不同粒度层级进行诊断性能对比。结果显示，音素级分析表现最优，AUROC达93.78% ± 2.34%，准确率为92.17% ± 2.43%。注意力分析表明，最具诊断意义的语音特征与临床标准一致：音素级为持续元音/a/、/e/、/o/、/i/，音节级为交替发音音节/ta/、/pa/、/la/、/ka/，词级为/pataka/序列。代码将公开于https://github.com/jetliqs/clearpd。
原文摘要 · Abstract (English)
Parkinson's Disease (PD) affects over 10 million people worldwide, with speech impairments in up to 89% of patients. Current speech-based detection systems analyze entire utterances, potentially overlooking the diagnostic value of specific phonetic elements. We developed a granularity-aware approach for multilingual PD detection using an automated pipeline that extracts time-aligned phonemes, syllables, and words from recordings. Using Italian, Spanish, and English datasets, we implemented a bidirectional LSTM with multi-head attention to compare diagnostic performance across the different granularity levels. Phoneme-level analysis achieved superior performance with AUROC of 93.78% +- 2.34% and accuracy of 92.17% +- 2.43%. This demonstrates enhanced diagnostic capability for cross-linguistic PD detection. Importantly, attention analysis revealed that the most informative speech features align with those used in established clinical protocols: sustained vowels (/a/, /e/, /o/, /i/) at phoneme level, diadochokinetic syllables (/ta/, /pa/, /la/, /ka/) at syllable level, and /pataka/ sequences at word level. Source code will be available at https://github.com/jetliqs/clearpd.
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。