English

StutterCut: Uncertainty-Guided Normalised Cut for Dysfluency Segmentation

Sound 2025-08-05 v1 Artificial Intelligence Audio and Speech Processing

Abstract

Detecting and segmenting dysfluencies is crucial for effective speech therapy and real-time feedback. However, most methods only classify dysfluencies at the utterance level. We introduce StutterCut, a semi-supervised framework that formulates dysfluency segmentation as a graph partitioning problem, where speech embeddings from overlapping windows are represented as graph nodes. We refine the connections between nodes using a pseudo-oracle classifier trained on weak (utterance-level) labels, with its influence controlled by an uncertainty measure from Monte Carlo dropout. Additionally, we extend the weakly labelled FluencyBank dataset by incorporating frame-level dysfluency boundaries for four dysfluency types. This provides a more realistic benchmark compared to synthetic datasets. Experiments on real and synthetic datasets show that StutterCut outperforms existing methods, achieving higher F1 scores and more precise stuttering onset detection.

Keywords

Cite

@article{arxiv.2508.02255,
  title  = {StutterCut: Uncertainty-Guided Normalised Cut for Dysfluency Segmentation},
  author = {Suhita Ghosh and Melanie Jouaiti and Jan-Ole Perschewski and Sebastian Stober},
  journal= {arXiv preprint arXiv:2508.02255},
  year   = {2025}
}

Comments

Accepted in Interspeech 2025

R2 v1 2026-07-01T04:33:01.532Z