Integrating gait and speech dynamics methodologies for enhanced stuttering detection across diverse datasets

<span lang="EN-US">Stuttering manifests as involuntary interruptions in the fluency of speech, often involving repetitions, prolongations, or blocks of sounds or syllables. These disruptions can significantly impact effective communication and psychosocial well-being. This research introduces a comprehensive system for speech impairment detection and gait analysis. Speech impairment, with a primary focus on stammer recognition, presents a multifaceted challenge in the field of speech processing. Stammers can manifest in various forms and detecting them accurately is a complex task. Our proposed methodology revolves around the development of StEnsembleNet, a neural network designed to learn spectral features at the frame level, enabling precise and efficient identification of speech impediments. Additionally, we extend our system's capabilities to the domain of gait analysis, leveraging a novel adaptive graph topology convolution network (AGT-ConvNet) for skeletal motion and visually enhanced topological learning to adapt to diverse visual environments and enhance the recognition of gait patterns. This research not only contributes to the field of speech therapy but also offers potential applications in healthcare and motion analysis.</span>