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

TL;DR

This paper introduces a semi-supervised learning framework for detecting medical conditions from speech dialogues, effectively leveraging unlabeled data through multi-level data modeling and achieving high performance with minimal labeled samples.

Contribution

It presents a novel hierarchical SSL approach that models frame, segment, and session levels, improving disease detection in speech with limited labeled data.

Findings

Achieves 90% of fully-supervised performance with only 11 labeled samples.

Framework is model-agnostic and robust across languages and conditions.

Effectively utilizes unlabeled clinical dialogues through pseudo-labeling.

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 https://github.com/fispresent/semi_pathological.