# A Comparative Study of Controllability, Explainability, and Performance in Dysfluency Detection Models

## TL;DR

This paper systematically compares four dysfluency detection models across performance, controllability, and explainability, highlighting trade-offs and guiding future development for clinical use.

## Contribution

It provides a comprehensive evaluation of four representative models, offering insights into their strengths, limitations, and practical deployment considerations for clinical applications.

## Key findings

- UDM achieves the best balance of accuracy and interpretability
- YOLO-Stutter and FluentNet are efficient but less transparent
- SSDM shows promise but was not fully reproducible

## Abstract

Recent advances in dysfluency detection have introduced a variety of modeling paradigms, ranging from lightweight object-detection inspired networks (YOLOStutter) to modular interpretable frameworks (UDM). While performance on benchmark datasets continues to improve, clinical adoption requires more than accuracy: models must be controllable and explainable. In this paper, we present a systematic comparative analysis of four representative approaches--YOLO-Stutter, FluentNet, UDM, and SSDM--along three dimensions: performance, controllability, and explainability. Through comprehensive evaluation on multiple datasets and expert clinician assessment, we find that YOLO-Stutter and FluentNet provide efficiency and simplicity, but with limited transparency; UDM achieves the best balance of accuracy and clinical interpretability; and SSDM, while promising, could not be fully reproduced in our experiments. Our analysis highlights the trade-offs among competing approaches and identifies future directions for clinically viable dysfluency modeling. We also provide detailed implementation insights and practical deployment considerations for each approach.