HASS: Hierarchical Simulation of Logopenic Aphasic Speech for Scalable PPA Detection

TL;DR

HASS is a new hierarchical simulation framework that models logopenic PPA speech deficits to improve diagnosis models amid data scarcity.

Contribution

It introduces a comprehensive, clinically grounded simulation method for lvPPA speech, capturing multi-level phenotypes for better detection.

Findings

Simulation improves detection accuracy.

Framework captures semantic, phonological, and temporal deficits.

Enables scalable PPA diagnosis with limited real data.

Abstract

Building a diagnosis model for primary progressive aphasia (PPA) has been challenging due to the data scarcity. Collecting clinical data at scale is limited by the high vulnerability of clinical population and the high cost of expert labeling. To circumvent this, previous studies simulate dysfluent speech to generate training data. However, those approaches are not comprehensive enough to simulate PPA as holistic, multi-level phenotypes, instead relying on isolated dysfluencies. To address this, we propose a novel, clinically grounded simulation framework, Hierarchical Aphasic Speech Simulation (HASS). HASS aims to simulate behaviors of logopenic variant of PPA (lvPPA) with varying degrees of severity. To this end, semantic, phonological, and temporal deficits of lvPPA are systematically identified by clinical experts, and simulated. We demonstrate that our framework enables more accurate and generalizable detection models.