Special Issues
Table of Content

Artificial Intelligence in Visual and Audio Signal Processing

Submission Deadline: 31 December 2025 View: 469 Submit to Special Issue

Guest Editors

Dr. Karolina Nurzyńska

Email: Karolina.Nurzynska@polsl.pl

Affiliation: Department of Algoritmics and Software, Silesian University of Technology, Gliwice, 44-100, Poland

Homepage:

Research Interests: machine learning, deep learning, deep neural network architectures, medical image analysis, large language models

图片3.png


Dr. Sebastian Iwaszenko

Email: siwaszenko@gig.eu

Affiliation: GIG National Research Institute, Katowice, 40-166, Poland

Homepage:

Research Interests: computer vision, machine learning, deep learning, artificial intelligence, industrial applications of AI tools and methods

图片4.png


Summary

The swift advancement of artificial intelligence techniques is astonishing. Deep learning models enable more accurate outcomes across all fields where they are implemented. The potential applications of these models, along with traditional machine learning, are becoming increasingly varied and diverse. Consequently, research in this area is becoming more demanding, and the results are quickly being integrated into everyday life.

This Special Issue emphasizes progress in the creation and enhancement of methods for processing visual and audio signals. The growing availability and accessibility of hardware for capturing these signals have resulted in a significant increase in data collection. However, the vast amount of data gathered necessitates the development of quicker and more efficient methods for analyzing and processing signal data. As data acquisition has become more straightforward and cost-effective, there is an increasing demand for automated processing and analysis to interpret the collected information.

In this Special Issue, we invite submissions that delve into pioneering research and recent progress in the field of visual and audio signal analysis across all possible domains. We particularly encourage submissions that present innovative approaches and assess their impact compared to the current state-of-the-art.


Keywords

image processing and understanding, image recognition, computer vision, multimodal images understanding, multispectral images understanding, visual attention, image denoising, knowledge discovery, image understanding applications, audio processing and understanding, frequency analysis, wavelet analysis, speech recognition, signal denoising, signal decomposition, timeseries analysis, features discovery, pattern recognition, pattern identification

Published Papers


  • Open Access

    ARTICLE

    MultiAgent-CoT: A Multi-Agent Chain-of-Thought Reasoning Model for Robust Multimodal Dialogue Understanding

    Ans D. Alghamdi
    CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.071210
    (This article belongs to the Special Issue: Artificial Intelligence in Visual and Audio Signal Processing)
    Abstract Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities. Current approaches struggle with cross-modal alignment, temporal consistency, and robust handling of noisy or incomplete inputs across multiple modalities. We propose MultiAgent-Chain of Thought (CoT), a novel multi-agent chain-of-thought reasoning framework where specialized agents for text, vision, and speech modalities collaboratively construct shared reasoning traces through inter-agent message passing and consensus voting mechanisms. Our architecture incorporates self-reflection modules, conflict resolution protocols, and dynamic rationale alignment to enhance consistency, factual accuracy, and user engagement. More >

Share Link