Machine learning for stuttering identification: Review, challenges and future directions

Stuttering is a speech disorder during which the flow of interrupted by involuntary pauses and repetition sounds. identification an interesting interdisciplinary domain research problem involving pathology, psychology, acoustics, signal processing, making it hard complicated to detect. Recent developments in machine deep learning have dramatically revolutionized domain, however minimal attention has been given stuttering identification. This work fills gap trying bring researchers together from fields. In this paper, we comprehensively review acoustic features, statistical learning-based stuttering/disfluency classification methods. We also present several challenges possible future directions.