Inclusive ASR Model for Dysarthria Speech
摘要
Dysarthria, a motor speech disorder, poses significant challenges to individuals in effectively communicating their thoughts and needs. To address this issue, our project aims to provide a platform leveraging speech recognition and voice assistive technology to facilitate improved communication for individuals with dysarthric speech. This research paper presents our approach, focusing on the utilization of Dynamic Time Warping (DTW) technique, a powerful method in speech processing, to enhance the accuracy and efficiency of speech recognition for dysarthric speech. We detail the design and implementation of our platform, emphasizing the integration of DTW within the system architecture. Additionally, we discuss the evaluation of our approach through empirical studies, demonstrating the effectiveness and utility of DTW in improving communication outcomes for individuals with dysarthria.