Results 61 to 70 of about 2,773 (174)

Resource‐Aware Contrastive Scattering Meta‐Learning for Efficient Few‐Shot Acoustic Anomaly Detection

Advanced Intelligent Systems, Volume 8, Issue 9, September 2026.
This paper introduces a resource‐aware Contrastive Scattering Meta‐Learning (CSML) framework for acoustic anomaly detection. By leveraging training‐free wavelet scattering and metric‐based meta‐learning, the model achieves competitive performance with only 50 K learnable parameters—a 98% reduction compared to state‐of‐the‐art frameworks—enabling ...
Rami Zewail, Bassem Mokhtar
wiley   +1 more source

Snoring Sound Recognition Using Multi-Channel Spectrograms

Archives of Acoustics
Obstructive sleep apnea-hypopnea syndrome (OSAHS) is a common and high-risk sleep-related breathing disorder. Snoring detection is a simple and non-invasive method. In many studies, the feature maps are obtained by applying a short-time Fourier transform
Ziqiang YE, Jianxin PENG, Xiaowen ZHANG, Lijuan SONG   +3 more
doaj   +1 more source

Acoustic emissions based structural diagnosis technique for steel details

ce/papers, Volume 9, Issue 2-3, Page 1817-1822, September 2026.
Abstract Acoustic emissions (AE) are a non‐destructive testing technique used to detect micro‐cracks and defects in industrial structures, including areas that are difficult to inspect visually. In steel structures, welded joints are particularly critical, as they are prone to damage mechanisms such as yielding and high‐cycle fatigue in bridges.
Roberto Andreotti, Gabriele Zanon, Rocco Di Filippo, Alessio Bonelli, Nicola Tondini, Oreste S. Bursi   +5 more
wiley   +1 more source

Exploring the Impact of Image-Based Audio Representations in Classification Tasks Using Vision Transformers and Explainable AI Techniques

Information
An important hurdle in medical diagnostics is the high-quality and interpretable classification of audio signals. In this study, we present an image-based representation of infant crying audio files to predict abnormal infant cries using a vision ...
Sari Masri, Ahmad Hasasneh, Mohammad Tami, Chakib Tadj   +3 more
doaj   +1 more source

An Automated Pipeline for Few‐Shot Bird Call Classification, a Case Study With the Tooth‐Billed Pigeon

Ecology and Evolution, Volume 16, Issue 9, September 2026.
This study presents an automated, few‐shot bird call classification pipeline designed to detect rare and critically endangered species using as few as one to three known vocalizations. Validated on both a simulated dataset and real‐world recordings of the Tooth‐Billed Pigeon, the model achieved high recall and accuracy, offering a practical tool for ...
Abhishek Jana, Moeumu Uili, James Atherton, Mark O'Brien, Joe Wood, Leandra Brickson   +5 more
wiley   +1 more source

Multi‐Modal AI Approach in Depression Detection and Treatment: A Systematic Review of Last Decade

WIREs Data Mining and Knowledge Discovery, Volume 16, Issue 3, September 2026.
Overview of multimodal approaches for depression detection and treatment. ABSTRACT Depression is a common and devastating mental health illness with serious personal and societal consequences. Despite advancing treatment techniques, there are still hurdles in the effective diagnosis and treatment of depression, such as prompt diagnosis, personalized ...
Smith K. Khare, Esmaeil S. Nadimi, U. Rajendra Acharya, Victoria Blanes‐Vidal   +3 more
wiley   +1 more source

Architectural Scalability and Attention Stabilization for Robust Impulsive Acoustic Spectrogram Classification Using Swin Transformer V2

IEEE Access
Impulsive acoustic event classification based on spectrogram representations remains challenging due to the non-stationary and broadband characteristics of transient signals.
Pafan Doungpaisan, Peerapol Khunarsa
doaj   +1 more source

A Systematic Review of Data Science in Early Voice‐Based Detection of Parkinson's and Amyotrophic Lateral Sclerosis Neurodegenerative Diseases

WIREs Data Mining and Knowledge Discovery, Volume 16, Issue 3, September 2026.
Seven‐stage AI‐powered voice biomarker pipeline for neurodegenerative disease diagnosis and clinical decision support. ABSTRACT Recent studies have shown that voice analysis provides a feasible, non‐invasive diagnostic alternative for the early detection of neurodegenerative diseases (NDs), such as Parkinson's disease (PD) and Amyotrophic Lateral ...
Abdulazeez Mousa, Fatih Özyurt, Ridwan Boya Marqas Shamoun, Laszlo Barna Iantovics   +3 more
wiley   +1 more source

Explainable Artificial Intelligence for Clinical Trust in Parkinson's Disease: A Scoping Review on Non‐Invasive Digital Biomarkers

WIREs Data Mining and Knowledge Discovery, Volume 16, Issue 3, September 2026.
Explainable artificial intelligence is expanding Parkinson's disease research by improving model transparency, supporting biomarker discovery and optimizing predictive models, but further validation and clinical integration are needed before routine healthcare implementation. ABSTRACT Parkinson's disease (PD) increasingly relies on non‐invasive digital
Lorenzo Rettori, Erika Rovini, Hamido Fujita, Filippo Cavallo   +3 more
wiley   +1 more source

Interpreting CNN models for musical instrument recognition using multi-spectrogram heatmap analysis: a preliminary study

Frontiers in Artificial Intelligence
IntroductionMusical instrument recognition is a critical component of music information retrieval (MIR), aimed at identifying and classifying instruments from audio recordings.
Rujia Chen, Akbar Ghobakhlou, Ajit Narayanan   +2 more
doaj   +1 more source