Acoustic-to-articulatory inversion (AAI) involves mapping from the acoustic to the articulatory space. Signal-processing features like the MFCCs, have been widely used for the AAI task. For subjects with dysarthric speech, AAI is challenging because of an imprecise and indistinct pronunciation. In this work, we perform AAI for dysarthric speech using representations from pre-trained self-supervised learning (SSL) models. We demonstrate the impact of different pre-trained features on this challenging AAI task, at low-resource conditions. In addition, we also condition x-vectors to the extracted SSL features to train a BLSTM network. In the seen case, we experiment with three AAI training schemes (subject-specific, pooled, and fine-tuned). The results, consistent across training schemes, reveal that DeCoAR, in the fine-tuned scheme, achieves a relative improvement of the Pearson Correlation Coefficient (CC) by ~1.81% and ~4.56% for healthy controls and patients, respectively, over MFCCs. We observe similar average trends for different SSL features in the unseen case. Overall, SSL networks like wav2vec, APC, and DeCoAR, trained with feature reconstruction or future timestep prediction tasks, perform well in predicting dysarthric articulatory trajectories.

翻译：声学-发音反演（AAI）涉及从声学空间到发音空间的映射。信号处理特征如MFCC已广泛应用于AAI任务。对于构音障碍语音的受试者，由于发音不精确且模糊不清，AAI具有挑战性。本研究利用预训练自监督学习（SSL）模型的表征对构音障碍语音进行AAI。我们展示了不同预训练特征在低资源条件下对该挑战性AAI任务的影响。此外，我们还将x-vectors与提取的SSL特征结合来训练BLSTM网络。在可见情况下，我们实验了三种AAI训练方案（特定受试者、池化和微调）。结果在各训练方案中一致，表明在微调方案中，DeCoAR相对于MFCC，在健康对照组和患者中分别实现了皮尔逊相关系数的相对提升约1.81%和4.56%。在不可见情况下，我们观察到不同SSL特征的相似平均趋势。总体而言，基于特征重构或未来时间步预测任务训练的SSL网络（如wav2vec、APC和DeCoAR）在预测构音障碍发音轨迹方面表现良好。