IEEE Open Journal of Signal Processing 2025

20 papers
The 2025 edition of the IEEE Open Journal of Signal Processing features 21 papers covering advancements in audio, image, and multidimensional signal processing. Research themes emphasize the integration of machine learning with signal analysis, specifically through generative class incremental learning and multi-label few-shot learning for audio tagging. Multimodal processing is a notable trend, seen in studies on text-guided image denoising and the use of spatio-temporal features for sign language assessment. In the field of acoustics and spatial audio, work includes Head-Related Transfer Function modeling using neural fields and improvements to music source separation. Other research focuses on computer vision and sensing, such as localized mesh editing with neural shaders and streaming LiDAR scene flow estimation. Frequent contributors to this volume include François G. Germain, Jonathan Le Roux, and Miki Haseyama. These publications indicate a focus on applying neural architectures to solve complex estimation and classification tasks in real-world scenarios.

Top Research Directions

The 14 research directions with IEEE Open Journal of Signal Processing 2025 papers, ranked by paper count, next to 2024. Share is the fraction of the edition’s papers in the direction.

#Direction20252024Share 2025Share 20242024 rank
1Data Quality and Acoustic Fidelity in Text to Speech105.0%0.0%—
2Decoupling Domain Adaptation from Network Architecture105.0%0.0%—
3Diffeomorphic Flows for Topology Preserving Deformation105.0%0.0%—
4Efficient Training and Inference for Diffusion Models105.0%0.0%—
5Mitigating Task Interference in Multi-Task Learning105.0%0.0%—
6Overcoming the Storage Bottleneck of Task Specific Model Replication105.0%0.0%—
7Restoring Images Directly in the RAW Sensor Domain105.0%0.0%—
8Restoring Visual Structure in Low Light Environments105.0%0.0%—
9Robust Speaker Verification Under Severe Data Constraints105.0%0.0%—
10Spoofing Aware Speaker Verification105.0%0.0%—
11Synergistic Multimodal Control for Generative Synthesis105.0%0.0%—
12Tensor Factorization for Parameter Efficient Model Adaptation105.0%0.0%—
13Test-Time Batch Normalization Adaptation105.0%0.0%—
14The Synthetic to Natural Domain Gap in Speech Models105.0%0.0%—

Download all directions as CSV

Institutions

Institutions credited by IEEE Open Journal of Signal Processing 2025 papers: a paper credits every institution named in its affiliations, once. 21 institutions share 7 credited papers.

#InstitutionPapersShare20242024 rank
1002cfhw56 114.3%0—
2Carnegie Mellon University 114.3%131
3EURECOM 114.3%12
4Keio University 114.3%113
5Korea Advanced Institute of Science and Technology 114.3%128
6Meta (United States) 114.3%19
7Mitsubishi Electric Research Laboratories (United States) 114.3%0—
8National Institute of Informatics 114.3%125
9National Technical University of Athens 114.3%116
10National University of Computer and Emerging Sciences 114.3%0—
11Queen Mary University of London 114.3%0—
12Renmin University of China 114.3%122
13Seoul National University 114.3%0—
14Shanghai Jiao Tong University 114.3%110
15Stony Brook University 114.3%130
16Technical University of Munich 114.3%0—
17Tel Aviv University 114.3%0—
18The University of Tokyo 114.3%127
19United States Air Force Research Laboratory 114.3%112
20University of California, Riverside 114.3%118
21Yonsei University 114.3%17

Download all institutions as CSV

About this data

Papers. IEEE Open Journal of Signal Processing 2025 lists 20 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers. Comparisons with 2024 use shares, since the edition went from 20 to 20 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 7 of 20 papers (35.0%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-17 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “IEEE Open Journal of Signal Processing 2025”, https://lacuna.tiptreesystems.com/venue/ieee-open-journal-of-signal-processing/2025.

Top Authors

AuthorPapers
Keisuke Maeda2
Miki Haseyama2
Takahiro Ogawa2
Ali H. Sayed1
Amit Roy-Chowdhury1
Ashley Prater-Bennette1
Driton Salihu1
Eckehard Steinbach1
Emmanouil Benetos1
Joon Son Chung1
Martin B. Møller1
Mert Kayaalp1
Nebiyou Yismaw1
Raja Giryes1
Rakib Hyder1
Salman Asif1
Shinji Watanabe1
Yash Garg1
Z. Jane Wang1

Impactful Papers

Papers from IEEE Open Journal of Signal Processing 2025 that shaped research clusters.

Influential

Papers

Title
Advancing the Frontiers of Deep Learning for Low-Dose 3D Cone-Beam CT Reconstruction
Bayesian Sound Field Estimation Using Moving Microphones
Embracing Cacophony: Explaining and Improving Random Mixing in Music Source Separation
Enhancing Classification Models With Sophisticated Counterfactual Images
Enhancing Generative Class Incremental Learning Performance With a Model Forgetting Approach
Feasibility Study of Location Authentication for IoT Data Using Power Grid Signatures
Formant Tracking by Combining Deep Neural Network and Linear Prediction
Hierarchical GraphCut Phase Unwrapping Based on Invariance of Diffeomorphisms Framework
LC-Protonets: Multi-Label Few-Shot Learning for World Music Audio Tagging
LEMON: Localized Editing With Mesh Optimization and Neural Shaders
LIMMITS'24: Multi-Speaker, Multi-Lingual INDIC TTS With Voice Cloning
Minimizing the Probability of Error for Decision Making Over Graphs
Parameter-Efficient Multi-Task and Multi-Domain Learning Using Factorized Tensor Networks
Posterior-Based Analysis of Spatio-Temporal Features for Sign Language Assessment
SMITIN: Self-Monitored Inference-Time INtervention for Generative Music Transformers
SpoofCeleb: Speech Deepfake Detection and SASV in the Wild
Streaming LiDAR Scene Flow Estimation
SuDaField: Subject- and Dataset-Aware Neural Field for HRTF Modeling
Task Nuisance Filtration for Unsupervised Domain Adaptation
Tell Me What You See: Text-Guided Real-World Image Denoising