https://arxiv.org/abs/2007.08003

This work attempts to detect and classify stutters in the input audio while existing works focus only on detection of stutters. We have used Gated Recurrent CNN on MFCC audio features for stutter detection and classification. We propose an SVM-based system that can suggest therapies based on the type and severity of the stuttering. We have also developed an Android app, Node.js based server and exploited Firebase for storing API requests and responses.