Weakly Supervised Phonological Features for Pathological Speech Analysis

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Thienpondt, Jenthe, Vanderreydt, Geoffroy, Hammami, Abdessalem, Demuynck, Kris
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909804139642880
author Thienpondt, Jenthe
Vanderreydt, Geoffroy
Hammami, Abdessalem
Demuynck, Kris
author_facet Thienpondt, Jenthe
Vanderreydt, Geoffroy
Hammami, Abdessalem
Demuynck, Kris
contents Paralinguistic properties of speech are essential in analyzing and choosing optimal treatment options for patients with speech disorders. However, automatic modeling of these characteristics is difficult due to the lack of labeled speech datasets describing paralinguistic properties, especially at the frame-level. In this paper, we propose a weakly supervised training method which exploits the known acoustic properties of phonemes by training an ASR model with an interpretable frame-level phonological feature bottleneck layer. Subsequently, we assess the viability of these phonological features in speech pathology analysis by developing corresponding models for intelligibility prediction and speech pathology classification. Models using our proposed phonological features perform similar to other state-of-the-art acoustic features on both tasks with a classification accuracy of 75% and a 8.43 RMSE on speech intelligibility prediction. In contrast to others, our phonological features are text-independent and highly interpretable, providing potentially useful insights for speech therapists.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19879
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Weakly Supervised Phonological Features for Pathological Speech Analysis
Thienpondt, Jenthe
Vanderreydt, Geoffroy
Hammami, Abdessalem
Demuynck, Kris
Audio and Speech Processing
Paralinguistic properties of speech are essential in analyzing and choosing optimal treatment options for patients with speech disorders. However, automatic modeling of these characteristics is difficult due to the lack of labeled speech datasets describing paralinguistic properties, especially at the frame-level. In this paper, we propose a weakly supervised training method which exploits the known acoustic properties of phonemes by training an ASR model with an interpretable frame-level phonological feature bottleneck layer. Subsequently, we assess the viability of these phonological features in speech pathology analysis by developing corresponding models for intelligibility prediction and speech pathology classification. Models using our proposed phonological features perform similar to other state-of-the-art acoustic features on both tasks with a classification accuracy of 75% and a 8.43 RMSE on speech intelligibility prediction. In contrast to others, our phonological features are text-independent and highly interpretable, providing potentially useful insights for speech therapists.
title Weakly Supervised Phonological Features for Pathological Speech Analysis
topic Audio and Speech Processing
url https://arxiv.org/abs/2509.19879