Systematic Review of Machine Learning Approaches for Detecting Developmental Stuttering

A systematic review of the literature on statistical and machine learning schemes for identifying symptoms developmental stuttering from audio recordings is reported. Twenty-seven papers met quality standards that were set. Comparison results across studies was not possible because training testing data, model architecture feature inputs varied studies. The limitations identified comparison included: no indication application work, data selected models in ways could lead to biases, used different datasets attempted locate symptom types, reported there standard way reporting performance statistics. Recommendations made about how these problems can be addressed future work this topic.