Sedigh Malekroodi Hadi, Madusanka Nuwan, Lee Byeong-Il, Yi Myunggi
Industry 4.0 Convergence Bionics Engineering, Pukyong National University, Busan 48513, Republic of Korea.
Digital Healthcare Research Center, Institute of Information Technology and Convergence, Pukyong National University, Busan 48513, Republic of Korea.
Bioengineering (Basel). 2025 Jul 1;12(7):728. doi: 10.3390/bioengineering12070728.
Diagnosing Parkinson's disease (PD) through speech analysis is a promising area of research, as speech impairments are often one of the early signs of the disease. This study investigates the efficacy of fine-tuning pre-trained Automatic Speech Recognition (ASR) models, specifically Wav2Vec 2.0 and HuBERT, for PD detection using transfer learning. These models, pre-trained on large unlabeled datasets, can be capable of learning rich speech representations that capture acoustic markers of PD. The study also proposes the integration of a supervised contrastive (SupCon) learning approach to enhance the models' ability to distinguish PD-specific features. Additionally, the proposed ASR-based features were compared against two common acoustic feature sets: mel-frequency cepstral coefficients (MFCCs) and the extended Geneva minimalistic acoustic parameter set (eGeMAPS) as a baseline. We also employed a gradient-based method, Grad-CAM, to visualize important speech regions contributing to the models' predictions. The experiments, conducted using the NeuroVoz dataset, demonstrated that features extracted from the pre-trained ASR models exhibited superior performance compared to the baseline features. The results also reveal that the method integrating SupCon consistently outperforms traditional cross-entropy (CE)-based models. Wav2Vec 2.0 and HuBERT with SupCon achieved the highest F1 scores of 90.0% and 88.99%, respectively. Additionally, their AUC scores in the ROC analysis surpassed those of the CE models, which had comparatively lower AUCs, ranging from 0.84 to 0.89. These results highlight the potential of ASR-based models as scalable, non-invasive tools for diagnosing and monitoring PD, offering a promising avenue for the early detection and management of this debilitating condition.
通过语音分析诊断帕金森病（PD）是一个很有前景的研究领域，因为语音障碍往往是该疾病的早期症状之一。本研究调查了使用迁移学习微调预训练的自动语音识别（ASR）模型（特别是Wav2Vec 2.0和HuBERT）用于PD检测的有效性。这些在大型未标记数据集上预训练的模型能够学习丰富的语音表示，捕捉PD的声学标记。该研究还提出集成监督对比（SupCon）学习方法，以增强模型区分PD特定特征的能力。此外，将所提出的基于ASR的特征与两个常见的声学特征集进行比较：梅尔频率倒谱系数（MFCC）和扩展的日内瓦简约声学参数集（eGeMAPS）作为基线。我们还采用了基于梯度的方法Grad-CAM来可视化对模型预测有贡献的重要语音区域。使用NeuroVoz数据集进行的实验表明，与基线特征相比，从预训练的ASR模型中提取的特征表现出更好的性能。结果还表明，集成SupCon的方法始终优于传统的基于交叉熵（CE）的模型。带有SupCon的Wav2Vec 2.0和HuBERT分别获得了最高的F1分数，分别为90.0%和88.99%。此外，它们在ROC分析中的AUC分数超过了CE模型，CE模型的AUC相对较低，范围从0.84到0.89。这些结果突出了基于ASR的模型作为可扩展、非侵入性工具用于诊断和监测PD的潜力，为这种使人衰弱的疾病的早期检测和管理提供了一条有前景的途径。
