OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE-ACM Transactions on Audio Speech and Language Processing is 37. 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 2022-06-01 to 2026-06-01.)

Article	Citations
Representation Learning With Hidden Unit Clustering for Low Resource Speech Applications	340
Decorrelation in Feedback Delay Networks	251
CET2: Modelling Topic Transitions for Coherent and Engaging Knowledge-Grounded Conversations	237
WDEA: The Structure and Semantic Fusion With Wasserstein Distance for Low-Resource Language Entity Alignment	185
$\mathcal {P}$owMix: A Versatile Regularizer for Multimodal Sentiment Analysis	178
Towards Generating Diverse Audio Captions via Adversarial Training	171
MO-Transformer: Extract High-Level Relationship Between Words for Neural Machine Translation	164
Refining Synthesized Speech Using Speaker Information and Phone Masking for Data Augmentation of Speech Recognition	136
DropAttack: A Random Dropped Weight Attack Adversarial Training for Natural Language Understanding	130
Reverberant Source Separation Using NTF With Delayed Subsources and Spatial Priors	117
Audio-Only Phonetic Segment Classification Using Embeddings Learned From Audio and Ultrasound Tongue Imaging Data	98
Envelope-Based Multichannel Noise Reduction for Cochlear Implant Applications	88
Generalizing Speaker Verification for Spoof Awareness in the Embedding Space	84
Attention-Based Speech Enhancement Using Human Quality Perception Modeling	82
Efficient Lightweight Speaker Verification With Broadcasting CNN-Transformer and Knowledge Distillation Training of Self-Attention Maps	77
Learning Discriminative Representations and Decision Boundaries for Open Intent Detection	71
Multi-Channel to Multi-Channel Noise Reduction and Reverberant Speech Preservation in Time-Varying Acoustic Scenes for Binaural Reproduction	70
Improvement of Accent Classification Models Through Grad-Transfer From Spectrograms and Gradient-Weighted Class Activation Mapping	62
A User-Centric Approach for Deep Residual-Echo Suppression in Double-Talk	61
Review of Methods for Automatic Speaker Verification	60
Enhancing Robustness of Speech Watermarking Using a Transformer-Based Framework Exploiting Acoustic Features	60
AudioLM: A Language Modeling Approach to Audio Generation	55
The VoxCeleb Speaker Recognition Challenge: A Retrospective	53
Adaptive Multi-Domain Dialogue State Tracking on Spoken Conversations	50
Label-Correction Capsule Network for Hierarchical Text Classification	48

COVID-19 Detection via Fusion of Modulation Spectrum and Linear Prediction Speech Features	48
IEEE Signal Processing Society Information	47
Pronunciation Dictionary-Free Multilingual Speech Synthesis Using Learned Phonetic Representations	42
Complex-Domain Pitch Estimation Algorithm for Narrowband Speech Signals	41
ReZero: Region-Customizable Sound Extraction	41
Emotion Prediction Oriented Method With Multiple Supervisions for Emotion-Cause Pair Extraction	41
Disentangled Text Representation Learning With Information-Theoretic Perspective for Adversarial Robustness	40
Knowledge-Guided Transformer for Joint Theme and Emotion Classification of Chinese Classical Poetry	39
Spherically Steerable Vector Differential Microphone Arrays	39
Enhanced Multi-Domain Dialogue State Tracker With Second-Order Slot Interactions	38
Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processing	38
Implicit Self-Supervised Language Representation for Spoken Language Diarization	38
Distinctive and Natural Speaker Anonymization via Singular Value Transformation-Assisted Matrix	37
Textless Unit-to-Unit Training for Many-to-Many Multilingual Speech-to-Speech Translation	37