Aiding Speech Therapy Using Audio And Video Processing

摘要

Speech-language pathologists perform assessments and therapy for various speech disorders including language drills, articulation-therapy, breathing exercises, etc. help early diagnosis and treatments. Our proposed model utilizes audio as well as video analysis to automate a part of the therapy that helps both patients and therapists. This paper proposes a platform to help detect distinguishing features and variations in speech patterns and early detection and progress of diseases such as Cerebral palsy, Parkinson’s, etc. This technology facilitates cost-effective face-to-face interaction between therapists and patients. The proposed method aims to make the entire treatment more convenient and effective.