Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.26795 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914427182252032 |
|---|---|
| author | Li, Harrison Wang, Kevin Cho, Cheol Jun Lian, Jiachen Rangwala, Rabab Guo, Chenxu Yang, Emma Kurteff, Lynn Ezzes, Zoe Keegan-Rodewald, Willa Vonk, Jet Ramkrishnan, Siddarth Antonicelli, Giada Miller, Zachary Tempini, Marilu Gorno Anumanchipalli, Gopala |
| author_facet | Li, Harrison Wang, Kevin Cho, Cheol Jun Lian, Jiachen Rangwala, Rabab Guo, Chenxu Yang, Emma Kurteff, Lynn Ezzes, Zoe Keegan-Rodewald, Willa Vonk, Jet Ramkrishnan, Siddarth Antonicelli, Giada Miller, Zachary Tempini, Marilu Gorno Anumanchipalli, Gopala |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_26795 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HASS: Hierarchical Simulation of Logopenic Aphasic Speech for Scalable PPA Detection Li, Harrison Wang, Kevin Cho, Cheol Jun Lian, Jiachen Rangwala, Rabab Guo, Chenxu Yang, Emma Kurteff, Lynn Ezzes, Zoe Keegan-Rodewald, Willa Vonk, Jet Ramkrishnan, Siddarth Antonicelli, Giada Miller, Zachary Tempini, Marilu Gorno Anumanchipalli, Gopala Audio and Speech Processing Artificial Intelligence Sound 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. |
| title | HASS: Hierarchical Simulation of Logopenic Aphasic Speech for Scalable PPA Detection |
| topic | Audio and Speech Processing Artificial Intelligence Sound |
| url | https://arxiv.org/abs/2603.26795 |