Skip to content
Conference

Digital Biomarkers for Laryngeal Health Detection: A Multi-Modal CNN Approach Integrating 2D-Bispectrum and High-Dimensional MFCCs

Sep 2026 · 2026 2nd International Conference on Electrical, Robotics and Intelligent Systems (ELECRIS) · pp. 42-47 · 0 citations · 18 references

Abstract

Identifying speech dysphonia remains a constant diagnostic difficulty because of the non-linear character of glottal turbulence. Critical phase coupling properties intrinsic in pathological vocal fold vibrations are sometimes missed by conventional second-order power spectra analyses. To tackle this, we suggest an inventive Dual-Branch Convolutional Neural Network (DB-CNN) architecture meant to simultaneously record high-dimensional spectral features and higher order statistics. The model processes Mel-Frequency Cepstral Coefficients (MFCC) and Bispectrum Magnitude Maps separately using a Late Fusion method based on a Directed Acyclic Graph (DAG). A balanced dataset $(\mathbf{N}=\mathbf{8 1 0})$ experiment shows a considerable evolutionary performance trend. Though a single-branch MFCC-13 model only reached 0.816% accuracy, adding third order statistics and increasing spectral resolution (MFCC 14-26) significantly boosted diagnostic effectiveness. With Sensitivity of 86.89% and Specificity of 90.55%, the suggested DB-CNN achieved a maximum Accuracy of 89.36%. With a Matthews Correlation Coefficient (MCC) of 0.7623, the model is clearly reliable and a strong diagnostic tool. These findings indicate that the interaction between high-order MFCCs and non-linear Bispectrum analysis produces a very efficient digital biomarker for dysphonia identification, therefore surpassing baseline fusion techniques dramatically.

View source

Similar papers

Open access Oct 2026

Efficient ResNet-based Deep Learning Model forAsthma and COPD Detection Using Short-TimeFourier Transform Spectrograms

A deep learning-based framework for the automated detection of asthma and chronic obstructive pulmonary disease using respiratory sound analysis, outperforming existing CNN, ResNet, and SVM-based methods.

G. Karthik, D. L. Padmaja, Nageswara Rao Medikondu et al. · 0 citations
Nov 2026

Integration of machine learning and signal processing for asthma severity classification using respiratory sounds

This work paves the way for non-invasive, objective, and clinically useful decision-making support in asthma therapy with the first CNN approach for the recognition of asthma severity, demonstrating that respiratory sound locations and phases reveal distinct characteristics.

F. G. Nabi, Asim Ghaffar, Abdullah Shahzad et al. · 0 citations

Multi-Modal Sleep Analysis for Cognitive Impairment Detection

This team developed an intermediate feature fusion pipeline leveraging multimodal foundation models: HuBERT for electrocardiogram (ECG), a BENDR-based convolutional architecture for electroencephalogram (EEG), and SleepFM for combined PSG.

M. Szafarczyk, Szymon Gaczoł, Tomasz Wiecek · 0 citations
Open access 2026

Explainable 1D-CNN for Automated Detection of Valvular Heart Diseases Using PCG Signals

Valvular heart diseases (VHDs) produce characteristic alterations in phonocardiogram (PCG) signals that can support automated screening. However, the limited interpretability of deep-learning models restricts their clinical acceptance. This study proposes an explainable one-dimensional convolutional neural network (1D-...

B. S. Rajeshwari, Arnab Sengupta, B. Divya et al. · 0 citations
Open access Oct 2026

Subject-independent Parkinson’s Disease Detection through A Lightweight Spectrotemporal Hybrid Network

Background: Vocal impairment constitutes a prominent prodromal biomarker for Parkinson’s disease (PD). However, existing deep learning solutions often rely on computationally intensive architectures or biased validation protocols. This study proposes the lightweight spectrotemporal hybrid network (LST-Net), a resource-...

Babak Masoudi · 0 citations
Preprint Oct 2026

Feature Scaling Beats Architecture Choice in Offline Respiratory Screening for Low-Resource Clinics

Deep models are the usual choice for respiratory sound classification, but in clinics without GPUs or connectivity that choice carries a cost. We compare classical and deep classifiers on a five-class respiratory-sound corpus of 1,211 clips (asthma, COPD, pneumonia, Bronchial, healthy) from 201 patient groups, with a 3...

A. Chilala, Cleophas Kadima, I. Anyaele et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.