Self-supervised learning for pathological speech detection

Speech production is a complex phenomenon in which the brain orchestrates a sequence of processes involving thought processing, motor planning, and the execution of articulatory movements. However, this intricate execution of various processes is susceptible to influence and disruption by various neurodegenerative pathological speech disorders, such as Parkinson’s disease, resulting in dysarthria, apraxia, and other conditions. These disorders lead to pathological speech characterized by abnormal speech patterns and imprecise articulation. In clinical settings, diagnosing these speech disorders typically involves auditory perceptual tests, which are time-consuming, and the diagnosis can vary among clinicians based on their experiences, biases, and cognitive load during the diagnosis. Additionally, unlike neurotypical speakers, patients with speech pathologies/impairments are unable to access various virtual assistants such as Alexa and Siri. To address these challenges, several automatic pathological speech detection approaches have been proposed. These approaches aim to provide efficient and accurate detection of speech disorders, thereby facilitating timely intervention and support for individuals affected by these conditions. These approaches mainly differ in two aspects: the input representations utilized and the classifiers employed. Due to the limited availability of data, the detection performance remains subpar. Self-supervised learning (SSL) embeddings, such as wav2vec2 and their multilingual versions, are being explored as a promising avenue for improving performance. These embeddings leverage self-supervised learning techniques to extract rich representations from audio data, thereby offering a potential solution to address the limitations posed by the scarcity of labeled data. Integrating self-supervised learning embeddings into pathological speech detection approaches could result in more robust and accurate models capable of handling diverse speech patterns and variations encountered in real-world scenarios.