A Comparative Study of Controllability, Explainability, and Performance in Dysfluency Detection Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915470679998464 |
|---|---|
| author | Zhang, Eric Wei, Li Chen, Sarah Wang, Michael |
| author_facet | Zhang, Eric Wei, Li Chen, Sarah Wang, Michael |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00058 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Comparative Study of Controllability, Explainability, and Performance in Dysfluency Detection Models Zhang, Eric Wei, Li Chen, Sarah Wang, Michael Artificial Intelligence 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. |
| title | A Comparative Study of Controllability, Explainability, and Performance in Dysfluency Detection Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.00058 |