发表机构
University of Maryland, College Park; Sylhet MAG Osmani Medical College Hospital; Dr. M R Khan Shishu Hospital & Institute of Child Health; Line Reflection Ltd.（马里兰大学学院公园分校; 锡尔赫特MAG奥斯马尼医学院医院; M R 汗儿童医院与儿童健康研究所; Line Reflection 有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出跨语言疾病对齐框架CL-DAF，从自发语音中识别跨语言一致的声学特征，提升呼吸疾病（如COPD）跨语言检测性能，为多语言临床语音模型奠定基础。
AI 中文摘要
自发语音为呼吸健康评估提供了一种可扩展、非侵入性的信号，然而，能够跨语言泛化的可解释模型仍具挑战性，因为疾病相关的声学变化受到语言特定语音变异的混淆。我们提出了CL-DAF，一个跨语言疾病对齐框架，用于识别疾病效应在语言间保持一致的声学维度。利用201名英语和75名新收集的孟加拉语说话者，我们构建了一个共同的272维声学表示，并使用符号秩双列效应和语言不变性评分来量化疾病对齐。我们首先表明，自发的孟加拉语语音能将COPD与对照组区分开来（AUC 0.85）；然而，133个特征在跨语言时逆转了其疾病方向，且完整表示迁移效果不佳（从孟加拉语到英语的AUC为0.49）。CL-DAF分离出26个疾病对齐特征，将英语到孟加拉语和孟加拉语到英语的AUC分别提升至0.825和0.722。这些发现为强调病理而非语言相关变异的多语言临床语音模型奠定了基础。
英文摘要
Spontaneous speech offers a scalable, noninvasive signal for respiratory health assessment, yet interpretable models that generalize across languages remain challenging because disease-related acoustic changes are confounded by language-specific phonetic variation. We present CL-DAF, a Cross-Lingual Disease-Alignment Framework that identifies acoustic dimensions whose disease effects remain consistent across languages. Using 201 English and 75 newly collected Bangla speakers, we construct a common 272-dimensional acoustic representation and quantify disease alignment using signed rank-biserial effects and the Language Invariance Score. We first show that spontaneous Bangla speech separates COPD from controls (AUC 0.85); however, 133 features reverse their disease direction across languages and the full representation transfers poorly (AUC 0.49 from Bangla to English). CL-DAF isolates 26 disease-aligned features that raise AUCs to 0.825 and 0.722 from English to Bangla and Bangla to English, respectively. These findings provide a foundation for multilingual clinical speech models emphasizing pathology over language-dependent variation.
CommentsUnder review
