Impact of Speech Mode in Automatic Pathological Speech Detection
This work addresses the challenge of detecting pathological speech in spontaneous settings, which is more convenient for real-world applications but less studied, representing an incremental advance by comparing existing method categories on new data.
The paper investigated how speech mode (controlled vs. spontaneous) affects automatic pathological speech detection, finding that classical machine learning approaches struggle with spontaneous speech, while deep learning methods show superior performance by extracting additional cues.
Automatic pathological speech detection approaches yield promising results in identifying various pathologies. These approaches are typically designed and evaluated for phonetically-controlled speech scenarios, where speakers are prompted to articulate identical phonetic content. While gathering controlled speech recordings can be laborious, spontaneous speech can be conveniently acquired as potential patients navigate their daily routines. Further, spontaneous speech can be valuable in detecting subtle and abstract cues of pathological speech. Nonetheless, the efficacy of automatic pathological speech detection for spontaneous speech remains unexplored. This paper analyzes the influence of speech mode on pathological speech detection approaches, examining two distinct categories of approaches, i.e., classical machine learning and deep learning. Results indicate that classical approaches may struggle to capture pathology-discriminant cues in spontaneous speech. In contrast, deep learning approaches demonstrate superior performance, managing to extract additional cues that were previously inaccessible in non-spontaneous speech