OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE-ACM Transactions on Audio Speech and Language Processing is 30. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2021-04-01 to 2025-04-01.)

Article	Citations
Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning	214
Low-Latency Active Noise Control Using Attentive Recurrent Network	183
CL-XABSA: Contrastive Learning for Cross-Lingual Aspect-Based Sentiment Analysis	151
Convolutive Transfer Function-Based Multichannel Nonnegative Matrix Factorization for Overdetermined Blind Source Separation	88
List of Reviewers	81
Dual Microphone Speech Enhancement Based on Statistical Modeling of Interchannel Phase Difference	73
Towards Maximizing a Perceptual Sweet Spot for Spatial Sound With Loudspeakers	68
Golden Gemini is All You Need: Finding the Sweet Spots for Speaker Verification	58
CET2: Modelling Topic Transitions for Coherent and Engaging Knowledge-Grounded Conversations	52
Multi-Cue Guided Semi-Supervised Learning Toward Target Speaker Separation in Real Environments	51
Lightweight Speaker Verification Using Transformation Module With Feature Partition and Fusion	47
One General Teacher for Multi-Data Multi-Task: A New Knowledge Distillation Framework for Discourse Relation Analysis	45
SANet: A Compressed Speech Encoder and Steganography Algorithm Independent Steganalysis Deep Neural Network	45
Cross-Domain Aspect-Based Sentiment Classification With Tripartite Graph Modeling	44
Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition	41
DropAttack: A Random Dropped Weight Attack Adversarial Training for Natural Language Understanding	40
On Ambisonic Source Separation With Spatially Informed Non-Negative Tensor Factorization	39
Statistical Analysis for Speaker Recognition Evaluation With Data Dependence and Three Score Distributions	39
Operation-Augmented Numerical Reasoning for Question Answering	38
JMS-QA: A Joint Hierarchical Architecture for Mental Health Question Answering	36
High-Fidelity and Pitch-Controllable Neural Vocoder Based on Unified Source-Filter Networks	36
Handover QG: Question Generation by Decoder Fusion and Reinforcement Learning	35
Review of Methods for Automatic Speaker Verification	34
Principled Comparisons for End-to-End Speech Recognition: Attention vs Hybrid at the 1000-Hour Scale	33
Spatial Analysis and Synthesis Methods: Subjective and Objective Evaluations Using Various Microphone Arrays in the Auralization of a Critical Listening Room	33

The VoxCeleb Speaker Recognition Challenge: A Retrospective	33
Multi-Level Interaction Based Knowledge Graph Completion	32
Dynamic Convolutional Neural Networks as Efficient Pre-Trained Audio Models	31
Cacophony: An Improved Contrastive Audio-Text Model	31
Dynamic Prompt-Driven Zero-Shot Relation Extraction	31