Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jan 10, 2026

Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition
12:49

Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition

Published on: July 13, 2019

17.9K

A Hybrid Cross-Attentive CNN-BiLSTM-Transformer Network for Dysarthria Severity Classification.

M S Remya1, Prakash Ishwar2, Prema Nedungadi3

  • 1Amrita School of Computing, Amritapuri, Amrita Vishwa Vidyapeetham, Kollam, Kerala, India. remyams@am.amrita.edu.

Scientific Reports
|November 26, 2025
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Generative AI in disability-inclusive learning: a bibliometric and systematic literature analysis.

Disability and rehabilitation. Assistive technology·2026
Same author

Processing-induced modulation of nutraceutical and anti-nutritional profiles of beetroot variants targeting enhanced iron retention.

Scientific reports·2026
Same author

A Lesion-aware Edge-based Graph Neural Network for Predicting Language Ability in Patients with Post-stroke Aphasia.

Machine learning in clinical neuroimaging : 7th international workshop, MLCN 2024, held in conjunction with MICCAI 2024, Marrakesh, Morocco, October 10, 2024, proceedings. MLCN (Workshop) (7th : 2024 : Marrakesh, Morocco)·2026
Same author

Assessing Dietary Patterns, Lifestyle Practices, and Forest Foods with Bioactive Potential to Address Micronutrient Deficiencies and Noncommunicable Diseases in Northeast India.

Nutrients·2025
Same author

Integrating LLMs and Knowledge Graphs for Medical AI: Advances, Challenges, and Future Directions.

IEEE journal of biomedical and health informatics·2025
Same author

Vision transformer-powered conversational agent for real-time Indian Sign Language e-governance accessibility.

Scientific reports·2025
Same journal

Serum vitamin D level and its association with vertigo frequency and severity in Meniere disease.

Scientific reports·2026
Same journal

PFA-Net: a physics-informed feature enhancement and attention network for interpretable bearing fault diagnosis under strong noise.

Scientific reports·2026
Same journal

Circulating inflammatory, redox, and apoptosis-related alterations in drug-naive idiopathic pulmonary fibrosis: an exploratory case-control study.

Scientific reports·2026
Same journal

A baseline-oriented dynamic aggregation approach for demand-side heterogeneous controllable resources.

Scientific reports·2026
Same journal

Temporal precision and accuracy in schizophrenia: an exploratory study.

Scientific reports·2026
Same journal

Prefrontal EEG spectral and nonlinear signatures of subthreshold depression during resting state and affectively valenced picture/video viewing: a participant-level analysis.

Scientific reports·2026
See all related articles

This study introduces a hybrid deep learning model for accurate dysarthria detection and severity classification. The novel approach significantly improves automated speech disorder assessment for early diagnosis and personalized treatment.

Area of Science:

  • Neurology
  • Speech Science
  • Artificial Intelligence

Background:

  • Dysarthria is a neurological speech disorder causing articulatory impairment due to muscle weakness.
  • Objective assessment of dysarthria is crucial for timely intervention and personalized management.
  • Current methods for dysarthria detection and classification have limitations in accuracy and clinical applicability.

Purpose of the Study:

  • To develop and evaluate a novel hybrid deep learning model for objective, automated detection and severity classification of dysarthria.
  • To investigate the efficacy of fusing wavelet-based scalogram images with acoustic features using a cross-attention mechanism.
  • To enhance the accuracy and clinical utility of automated speech disorder assessment.

Main Methods:

Keywords:
Dysarthria detectionScalogramsSeverity assessmentSpeech processingTORGOUA‑Speech

Related Experiment Videos

Last Updated: Jan 10, 2026

Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition
12:49

Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition

Published on: July 13, 2019

17.9K
  • A hybrid deep learning model integrating Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Transformer architectures was proposed.
  • A unique cross-attention mechanism was employed to fuse wavelet-based scalogram images with seven acoustic features (e.g., MFCCs, spectral descriptors).
  • The model was evaluated on two public datasets (TORGO, UA Speech) using binary detection and multi-class severity classification tasks, with cross-dataset testing and tenfold cross-validation.

    • Main Results:

    • State-of-the-art accuracies were achieved: 98.74% and 99.86% for binary dysarthria detection, and 95.69% and 97.91% for multi-class severity classification.
    • The proposed model significantly outperformed an MFCC baseline (p < 0.01) in detecting subtle dysarthric cues.
    • Robustness was confirmed through cross-dataset testing and tenfold cross-validation.

    Conclusions:

    • The multimodal cross-attention feature fusion significantly enhances the accuracy of automated dysarthria detection and severity classification.
    • This advanced approach improves the clinical applicability of speech disorder assessment tools.
    • The findings support early diagnosis and personalized treatment planning for individuals with dysarthria.