OOIR: Observatory of International Research

Papers

(The H4-Index of IEEE-ACM Transactions on Audio Speech and Language Processing is 42. 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 2022-01-01 to 2026-01-01.)

Article	Citations
Representation Learning With Hidden Unit Clustering for Low Resource Speech Applications	401
Decorrelation in Feedback Delay Networks	287
CET2: Modelling Topic Transitions for Coherent and Engaging Knowledge-Grounded Conversations	263
WDEA: The Structure and Semantic Fusion With Wasserstein Distance for Low-Resource Language Entity Alignment	187
$\mathcal {P}$owMix: A Versatile Regularizer for Multimodal Sentiment Analysis	173
Audio-Only Phonetic Segment Classification Using Embeddings Learned From Audio and Ultrasound Tongue Imaging Data	133
The Harmonic Shift Algorithm for Efficient Multi-Pitch Detection	132
Review of Methods for Automatic Speaker Verification	125
Similarity Measurement of Segment-Level Speaker Embeddings in Speaker Diarization	105
Efficient Lightweight Speaker Verification With Broadcasting CNN-Transformer and Knowledge Distillation Training of Self-Attention Maps	100
SBSim: A Sentence-BERT Similarity-Based Evaluation Metric for Indian Language Neural Machine Translation Systems	94
Attention-Based Speech Enhancement Using Human Quality Perception Modeling	77
Enhancing Robustness of Speech Watermarking Using a Transformer-Based Framework Exploiting Acoustic Features	77
Multi-Channel to Multi-Channel Noise Reduction and Reverberant Speech Preservation in Time-Varying Acoustic Scenes for Binaural Reproduction	75
Improvement of Accent Classification Models Through Grad-Transfer From Spectrograms and Gradient-Weighted Class Activation Mapping	72
Learning Phone Recognition From Unpaired Audio and Phone Sequences Based on Generative Adversarial Network	66
Generalizing Speaker Verification for Spoof Awareness in the Embedding Space	63
A User-Centric Approach for Deep Residual-Echo Suppression in Double-Talk	63
MO-Transformer: Extract High-Level Relationship Between Words for Neural Machine Translation	61
Refining Synthesized Speech Using Speaker Information and Phone Masking for Data Augmentation of Speech Recognition	61
Interpretable Multimodal Capsule Fusion	58
Envelope-Based Multichannel Noise Reduction for Cochlear Implant Applications	58
Comparison of Feature Extraction Methods for Sound-Based Classification of Honey Bee Activity	53
Multi-Level Time-Frequency Bins Selection for Direction of Arrival Estimation Using a Single Acoustic Vector Sensor	53
Learning Discriminative Representations and Decision Boundaries for Open Intent Detection	53

The VoxCeleb Speaker Recognition Challenge: A Retrospective	52
Reverberant Source Separation Using NTF With Delayed Subsources and Spatial Priors	52
Towards Generating Diverse Audio Captions via Adversarial Training	47
Inference Skipping for More Efficient Real-Time Speech Enhancement With Parallel RNNs	47
DropAttack: A Random Dropped Weight Attack Adversarial Training for Natural Language Understanding	47
AudioLM: A Language Modeling Approach to Audio Generation	47
Adaptive Multi-Domain Dialogue State Tracking on Spoken Conversations	47
Label-Correction Capsule Network for Hierarchical Text Classification	46
End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations	46
Integrated Syntactic and Semantic Tree for Targeted Sentiment Classification Using Dual-Channel Graph Convolutional Network	44
IEEE Signal Processing Society Information	44
Implicit Self-Supervised Language Representation for Spoken Language Diarization	44
COVID-19 Detection via Fusion of Modulation Spectrum and Linear Prediction Speech Features	44
SPEC: Summary Preference Decomposition for Low-Resource Abstractive Summarization	43
Pronunciation Dictionary-Free Multilingual Speech Synthesis Using Learned Phonetic Representations	43
Neural Coupled Sequence Labeling for Heterogeneous Annotation Conversion	42
Source Separation of Piano Concertos Using Musically Motivated Augmentation Techniques	42