Variable STFT layered CNN model for automated dysarthria detection and severity assessment using raw speech

K Radha, M Bansal, VR Dhulipalla - Circuits, Systems, and Signal …, 2024 - Springer
This paper presents a novel approach for automated dysarthria detection and severity
assessment using a variable short-time Fourier transform layered convolutional neural …

Automated detection and severity assessment of dysarthria using raw speech

K Radha, M Bansal - 2023 14th International Conference on …, 2023 - ieeexplore.ieee.org
Dysarthria is a medical condition that impairs an individual's ability to speak clearly due to
muscle weakness or paralysis. To diagnose and monitor dysarthria severity, this article …

Detecting Speech Abnormalities With a Perceiver-Based Sequence Classifier that Leverages a Universal Speech Model

H Soltau, I Shafran, A Ottenwess… - 2023 IEEE Automatic …, 2023 - ieeexplore.ieee.org
We propose a Perceiver-based sequence classifier to detect abnormalities in speech
reflective of several neurological disorders. We combine this classifier with a Universal …

WavRx: a Disease-Agnostic, Generalizable, and Privacy-Preserving Speech Health Diagnostic Model

Y Zhu, T Falk - IEEE Journal of Biomedical and Health …, 2024 - ieeexplore.ieee.org
Speech is known to carry health-related attributes, which has emerged as a novel venue for
remote and long-term health monitoring. However, existing models are usually tailored for a …

[PDF][PDF] Test-time adaptation for automatic pathological speech detection in noisy environments

M Amiri, I Kodrasi - Proc. European Signal Processing …, 2024 - publications.idiap.ch
Deep learning-based pathological speech detection approaches are gaining popularity as a
diagnostic tool to support time-consuming and subjective clinical assessments. While these …

[PDF][PDF] Adversarial Robustness Analysis in Automatic Pathological Speech Detection Approaches

M Amiri, I Kodrasi - Proc. Annual Conference of the …, 2024 - publications.idiap.ch
Automatic pathological speech detection relies on deep learning (DL), showing promising
performance for various pathologies. Despite the critical importance of robustness in …

Selfsupervised learning for pathological speech detection

SA Sheikh - arXiv preprint arXiv:2406.02572, 2024 - arxiv.org
Speech production is a complex phenomenon, wherein the brain orchestrates a sequence
of processes involving thought processing, motor planning, and the execution of articulatory …

Graph Neural Networks for Parkinsons Disease Detection

SA Sheikh, Y Kaloga, I Kodrasi - arXiv preprint arXiv:2409.07884, 2024 - arxiv.org
Despite the promising performance of state of the art approaches for Parkinsons Disease
(PD) detection, these approaches often analyze individual speech segments in isolation …

Impact of Speech Mode in Automatic Pathological Speech Detection

SA Sheikh, I Kodrasi - arXiv preprint arXiv:2406.09968, 2024 - arxiv.org
Automatic pathological speech detection approaches yield promising results in identifying
various pathologies. These approaches are typically designed and evaluated for …

Multiview Canonical Correlation Analysis for Automatic Pathological Speech Detection

Y Kaloga, SA Sheikh, I Kodrasi - arXiv preprint arXiv:2409.17276, 2024 - arxiv.org
Recently proposed automatic pathological speech detection approaches rely on
spectrogram input representations or wav2vec2 embeddings. These representations may …