Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Yu-Wen, Hirschberg, Julia
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.22972
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913917297491968
author Chen, Yu-Wen
Hirschberg, Julia
author_facet Chen, Yu-Wen
Hirschberg, Julia
contents The automatic assessment of health-related acoustic cues has the potential to improve healthcare accessibility and affordability. Although parametric models are promising, they face challenges in privacy and adaptability. To address these, we propose a NoN-Parametric framework for Speech-based symptom Assessment (NoNPSA). By isolating medical data in a retrieval datastore, NoNPSA avoids encoding private information in model parameters and enables efficient data updates. A self-supervised learning (SSL) model pre-trained on general-purpose datasets extracts features, which are used for similarity-based retrieval. Metadata-aware refinement filters the retrieved data, and associated labels are used to compute an assessment score. Experimental results show that NoNPSA achieves competitive performance compared to fine-tuning SSL-based methods, while enabling greater privacy, update efficiency, and adaptability--showcasing the potential of non-parametric approaches in healthcare.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22972
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptable Non-parametric Approach for Speech-based Symptom Assessment: Isolating Private Medical Data in a Retrieval Datastore
Chen, Yu-Wen
Hirschberg, Julia
Audio and Speech Processing
The automatic assessment of health-related acoustic cues has the potential to improve healthcare accessibility and affordability. Although parametric models are promising, they face challenges in privacy and adaptability. To address these, we propose a NoN-Parametric framework for Speech-based symptom Assessment (NoNPSA). By isolating medical data in a retrieval datastore, NoNPSA avoids encoding private information in model parameters and enables efficient data updates. A self-supervised learning (SSL) model pre-trained on general-purpose datasets extracts features, which are used for similarity-based retrieval. Metadata-aware refinement filters the retrieved data, and associated labels are used to compute an assessment score. Experimental results show that NoNPSA achieves competitive performance compared to fine-tuning SSL-based methods, while enabling greater privacy, update efficiency, and adaptability--showcasing the potential of non-parametric approaches in healthcare.
title Adaptable Non-parametric Approach for Speech-based Symptom Assessment: Isolating Private Medical Data in a Retrieval Datastore
topic Audio and Speech Processing
url https://arxiv.org/abs/2506.22972