OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE-ACM Transactions on Audio Speech and Language Processing is 39. 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 2022-08-01 to 2026-08-01.)

Article	Citations
Decorrelation in Feedback Delay Networks	367
CET2: Modelling Topic Transitions for Coherent and Engaging Knowledge-Grounded Conversations	282
WDEA: The Structure and Semantic Fusion With Wasserstein Distance for Low-Resource Language Entity Alignment	255
Towards Generating Diverse Audio Captions via Adversarial Training	199
MO-Transformer: Extract High-Level Relationship Between Words for Neural Machine Translation	195
DropAttack: A Random Dropped Weight Attack Adversarial Training for Natural Language Understanding	181
Reverberant Source Separation Using NTF With Delayed Subsources and Spatial Priors	179
Audio-Only Phonetic Segment Classification Using Embeddings Learned From Audio and Ultrasound Tongue Imaging Data	142
Generalizing Speaker Verification for Spoof Awareness in the Embedding Space	140
Multi-Channel to Multi-Channel Noise Reduction and Reverberant Speech Preservation in Time-Varying Acoustic Scenes for Binaural Reproduction	135
Review of Methods for Automatic Speaker Verification	114
Refining Synthesized Speech Using Speaker Information and Phone Masking for Data Augmentation of Speech Recognition	94
Improvement of Accent Classification Models Through Grad-Transfer From Spectrograms and Gradient-Weighted Class Activation Mapping	88
$\mathcal {P}$owMix: A Versatile Regularizer for Multimodal Sentiment Analysis	85
Envelope-Based Multichannel Noise Reduction for Cochlear Implant Applications	82
Efficient Lightweight Speaker Verification With Broadcasting CNN-Transformer and Knowledge Distillation Training of Self-Attention Maps	76
A User-Centric Approach for Deep Residual-Echo Suppression in Double-Talk	74
AudioLM: A Language Modeling Approach to Audio Generation	66
Learning Discriminative Representations and Decision Boundaries for Open Intent Detection	65
The VoxCeleb Speaker Recognition Challenge: A Retrospective	65
Enhancing Robustness of Speech Watermarking Using a Transformer-Based Framework Exploiting Acoustic Features	64
Attention-Based Speech Enhancement Using Human Quality Perception Modeling	61
Representation Learning With Hidden Unit Clustering for Low Resource Speech Applications	55
Adaptive Multi-Domain Dialogue State Tracking on Spoken Conversations	52
COVID-19 Detection via Fusion of Modulation Spectrum and Linear Prediction Speech Features	51

Pronunciation Dictionary-Free Multilingual Speech Synthesis Using Learned Phonetic Representations	49
IEEE Signal Processing Society Information	49
Emotion Prediction Oriented Method With Multiple Supervisions for Emotion-Cause Pair Extraction	48
Disentangled Text Representation Learning With Information-Theoretic Perspective for Adversarial Robustness	45
Complex-Domain Pitch Estimation Algorithm for Narrowband Speech Signals	45
ReZero: Region-Customizable Sound Extraction	45
Spherically Steerable Vector Differential Microphone Arrays	43
Implicit Self-Supervised Language Representation for Spoken Language Diarization	42
Enhanced Multi-Domain Dialogue State Tracker With Second-Order Slot Interactions	41
Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processing	41
Distinctive and Natural Speaker Anonymization via Singular Value Transformation-Assisted Matrix	40
Phrase-Aware Financial Sentiment Analysis Based on Constituent Syntax	40
SPEC: Summary Preference Decomposition for Low-Resource Abstractive Summarization	40
Predicting Level-Dependent Changes in Concurrent Vowel Scores Using the 2D-CNN Models	40
Textless Unit-to-Unit Training for Many-to-Many Multilingual Speech-to-Speech Translation	39
Integrated Syntactic and Semantic Tree for Targeted Sentiment Classification Using Dual-Channel Graph Convolutional Network	39