Stuttering is a widespread speech disorder affecting people globally, and it impacts effective communication and quality of life. Recent advancements in artificial intelligence (AI) and computational intelligence have introduced new possibilities for augmenting stuttering detection and treatment procedures. In this systematic review, the latest AI advancements and computational intelligence techniques in the context of stuttering are explored. By examining the existing literature, we investigated the application of AI in accurately determining and classifying stuttering manifestations. Furthermore, we explored how computational intelligence can contribute to developing innovative assessment tools and intervention strategies for persons who stutter (PWS). We reviewed and analyzed 14 refereed journal articles that were indexed on the Web of Science from 2019 onward. The potential of AI and computational intelligence in revolutionizing stuttering assessment and treatment, which can enable personalized and effective approaches, is also highlighted in this review. By elucidating these advancements, we aim to encourage further research and development in this crucial area, enhancing in due course the lives of PWS.

Background/Objectives: Disfluencies such as repetitions, prolongations, interjections, and blocks in sounds, syllables, or words can sometimes hinder communication. Currently, disfluencies are manually measured, which has inherent limitations, such as being time-consuming and subjective, which can lead to inconsistencies in measurement. Methods: To address these challenges, this study presents an innovative automated system for detecting disfluencies utilizing advanced artificial intelligence technologies; specifically, deep learning models such as convolutional neural networks (CNN) and convolutional long short-term memory (ConvLSTM). The system was evaluated using two benchmark datasets: FluencyBank and SEP-28K. Results: Our proposed system demonstrates remarkable performance, achieving detection accuracies of 0.97 and 0.96, respectively, for CNNs and ConvLSTM models. These results not only exceed those of prior studies but also highlight the effectiveness of our approach in enhancing stuttering evaluation. Conclusions: By providing a reliable and efficient tool for professionals in therapeutic settings, our system represents a significant advancement in the field, offering improved outcomes for individuals affected by stuttering.