Automatic stuttering detection and classification

Stuttering is a common speech disorder that affects the fluency of spoken language, and can have a significant impact on an individual's social and emotional well-being. Automatic stuttering detection and classification refers to the use of machine learning algorithms and natural language processing techniques to identify and classify instances of stuttering in spoken language. These techniques have the potential to improve the diagnosis and treatment of stuttering, as well as to support individuals with this disorder in their daily lives. However, the development of automatic stuttering detection and classification systems is challenging due to the variability in stuttering across individuals and languages and also the lack of large public dataset. We used Stuttering Events in Podcast-28k (SEP-28k) dataset and experimented with different feature sets on Long Short-Term Memory(LSTM) model to automatically detect stuttering and classify it.