Revisiting Rule-Based Stuttering Detection: A Comprehensive Analysis of Interpretable Models for Clinical Applications

TL;DR

This paper analyzes rule-based stuttering detection methods, enhancing their interpretability and performance, especially for clinical use, by integrating acoustic features and hierarchical decision structures, and compares them with neural approaches.

Contribution

It introduces an improved rule-based framework with speaking-rate normalization and hierarchical decisions, demonstrating competitive accuracy and interpretability for clinical applications.

Findings

Rule-based systems achieve 97-99% accuracy in prolongation detection.

They maintain stable performance across different speaking rates.

Rule-based models can be integrated with modern AI systems as proposal generators.

Abstract

Stuttering affects approximately 1% of the global population, impacting communication and quality of life. While recent advances in deep learning have pushed the boundaries of automatic speech dysfluency detection, rule-based approaches remain crucial for clinical applications where interpretability and transparency are paramount. This paper presents a comprehensive analysis of rule-based stuttering detection systems, synthesizing insights from multiple corpora including UCLASS, FluencyBank, and SEP-28k. We propose an enhanced rule-based framework that incorporates speaking-rate normalization, multi-level acoustic feature analysis, and hierarchical decision structures. Our approach achieves competitive performance while maintaining complete interpretability-critical for clinical adoption. We demonstrate that rule-based systems excel particularly in prolongation detection (97-99% accuracy) and provide stable performance across varying speaking rates. Furthermore, we show how these interpretable models can be integrated with modern machine learning pipelines as proposal generators or constraint modules, bridging the gap between traditional speech pathology practices and contemporary AI systems. Our analysis reveals that while neural approaches may achieve marginally higher accuracy in unconstrained settings, rule-based methods offer unique advantages in clinical contexts where decision auditability, patient-specific tuning, and real-time feedback are essential.