Evaluating the Performance of wav2vec Embedding for Parkinson's Disease Detection

Speech is one of the most serious manifestations of Parkinson's disease (PD). Sophisticated language/speech models have already demonstrated impressive performance on a variety of tasks, including classification. By analysing large amounts of data from a given setting, these models can identify patterns that would be difficult for clinicians to detect. We focus on evaluating the performance of a large self-supervised speech representation model, wav2vec, for PD classification. Based on the computed wav2vec embedding for each available speech signal, we calculated two sets of 512 derived features, wav2vec-sum and wav2vec-mean. Unlike traditional signal processing methods, this approach can learn a suitable representation of the signal directly from the data without requiring manual or hand-crafted feature extraction. Using an ensemble random forest classifier, we evaluated the embedding-based features on three different healthy vs. PD datasets (participants rhythmically repeat syllables /pa/, Italian dataset and English dataset). The obtained results showed that the wav2vec signal representation was accurate, with a minimum area under the receiver operating characteristic curve (AUROC) of 0.77 for the /pa/ task and the best AUROC of 0.98 for the Italian speech classification. The findings highlight the potential of the generalisability of the wav2vec features and the performance of these features in the cross-database scenarios.