OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE-ACM Transactions on Audio Speech and Language Processing is 36. 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 2022-05-01 to 2026-05-01.)

Article	Citations
Representation Learning With Hidden Unit Clustering for Low Resource Speech Applications	330
Decorrelation in Feedback Delay Networks	246
CET2: Modelling Topic Transitions for Coherent and Engaging Knowledge-Grounded Conversations	232
WDEA: The Structure and Semantic Fusion With Wasserstein Distance for Low-Resource Language Entity Alignment	179
$\mathcal {P}$owMix: A Versatile Regularizer for Multimodal Sentiment Analysis	173
Towards Generating Diverse Audio Captions via Adversarial Training	164
MO-Transformer: Extract High-Level Relationship Between Words for Neural Machine Translation	154
A User-Centric Approach for Deep Residual-Echo Suppression in Double-Talk	133
Refining Synthesized Speech Using Speaker Information and Phone Masking for Data Augmentation of Speech Recognition	128
DropAttack: A Random Dropped Weight Attack Adversarial Training for Natural Language Understanding	111
Reverberant Source Separation Using NTF With Delayed Subsources and Spatial Priors	93
Audio-Only Phonetic Segment Classification Using Embeddings Learned From Audio and Ultrasound Tongue Imaging Data	86
Envelope-Based Multichannel Noise Reduction for Cochlear Implant Applications	83
Generalizing Speaker Verification for Spoof Awareness in the Embedding Space	81
Multi-Channel to Multi-Channel Noise Reduction and Reverberant Speech Preservation in Time-Varying Acoustic Scenes for Binaural Reproduction	74
Improvement of Accent Classification Models Through Grad-Transfer From Spectrograms and Gradient-Weighted Class Activation Mapping	71
Learning Discriminative Representations and Decision Boundaries for Open Intent Detection	70
Review of Methods for Automatic Speaker Verification	59
Enhancing Robustness of Speech Watermarking Using a Transformer-Based Framework Exploiting Acoustic Features	58
The VoxCeleb Speaker Recognition Challenge: A Retrospective	58
Efficient Lightweight Speaker Verification With Broadcasting CNN-Transformer and Knowledge Distillation Training of Self-Attention Maps	57
Attention-Based Speech Enhancement Using Human Quality Perception Modeling	55
AudioLM: A Language Modeling Approach to Audio Generation	52
Adaptive Multi-Domain Dialogue State Tracking on Spoken Conversations	49
Label-Correction Capsule Network for Hierarchical Text Classification	47

COVID-19 Detection via Fusion of Modulation Spectrum and Linear Prediction Speech Features	46
Implicit Self-Supervised Language Representation for Spoken Language Diarization	46
IEEE Signal Processing Society Information	42
Pronunciation Dictionary-Free Multilingual Speech Synthesis Using Learned Phonetic Representations	41
SPEC: Summary Preference Decomposition for Low-Resource Abstractive Summarization	41
Hate Speech Detection via Dual Contrastive Learning	40
Emotion Prediction Oriented Method With Multiple Supervisions for Emotion-Cause Pair Extraction	38
Source Separation of Piano Concertos Using Musically Motivated Augmentation Techniques	37
Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach	37
Sound Field Estimation Based on Physics-Constrained Kernel Interpolation Adapted to Environment	37
Audio-Visual Cross-Attention Network for Robotic Speaker Tracking	37
ReZero: Region-Customizable Sound Extraction	36