Semi-Supervised Diseased Detection from Speech Dialogues with Multi-Level Data Modeling

Xingyuan Li, Mengyue WuSubmission to ICLR 2026 · Withdrawn

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recording. This task is further hampered by severe data scarcity and the subjective nature of clinical annotations. While semi-supervised learning (SSL) offers a viable path to leverage unlabeled data, existing audio methods often fail to address the core challenge that pathological traits are not uniformly expressed in a patient's speech. We propose a novel, audio-only SSL framework that explicitly models this hierarchy by jointly learning from frame-level, segment-level, and session-level representations within unsegmented clinical dialogues. Our end-to-end approach dynamically aggregates these multi-granularity features and generates high-quality pseudo-labels to efficiently utilize unlabeled data. Extensive experiments show the framework is model-agnostic, robust across languages and conditions, and highly data-efficient—achieving, for instance, 90\% of fully-supervised performance using only 11 labeled samples. This work provides a principled approach to learning from weak, far-end supervision in medical speech analysis. The code is available at \url{https://anonymous.4open.science/r/semi_pathological-93F8}.
BibTeX
@inproceedings{li2026semi,
  author = {Xingyuan Li and Mengyue Wu},
  title = {{Semi-Supervised Diseased Detection from Speech Dialogues with Multi-Level Data Modeling}},
  booktitle = {Annual Meeting of the Association for Computational Linguistics},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1194},
}
Figure