Latest Research in Machine Learning

Top Research Topics in Machine Learning

• Sound — 18 papers
• Audio and Speech Processing — 16 papers
• Computation and Language — 2 papers
• Speech and Audio Processing — 2 papers
• Machine Learning — 1 papers
• Signal Processing — 1 papers
• Speech Recognition and Synthesis — 1 papers
• Artificial Intelligence — 1 papers

Highest-Cited Papers

1. Hybrid Real- and Complex-Valued Neural Network Architecture for Speech Enhancement
2. Rethinking Language Model-Based Generative Speech Enhancement in the Latent Space of a Neural Audio Codec
3. RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation
4. Training Set Synthesis for Bioacoustic Denoising: A Case Study With Mice
5. BiTSE: Binaural Target Speaker Extraction in Noisy Multi-Talker Environments for AR Glass Arrays
6. Neural Array-Generic Direction-of-Arrival Estimation Exploiting Array Transfer Functions
7. Structured Phonological Representations for Audio-Articulatory rtMRI Speech Classification
8. DAVE: A Decoupled Audio-Visual Enhancement Framework for Real-World Speech Separation
9. BAMU: Bitstream-Aware Marginal-Utility Allocation for Frozen Pretrained Neural Speech Codecs
10. Mitigating Over-Suppression in Speech Enhancement via Inference-Time Rethink-and-Refine Correction Module
11. Cloud-Boosted Low-Compute Multi-Channel Speech Enhancement
12. Blind Speech SNR Estimation via Neural Speech Enhancement: An Enhance-and-Subtract Approach and Benchmark Against Classical Estimators
13. Blind Speech SNR Estimation via Neural Speech Enhancement: An Enhance-and-Subtract Approach and Benchmark Against Classical Estimators
14. cSTMM: A Unified Complex Spherical Student's $t$ Mixture Model for Directional Statistics in Mask-Based Blind Speech Separation
15. Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning
16. Multi Codec Discrete Diffusion Model for Text Guided Speech Inpainting and Editing
17. Echo-Aware Modulation for Compact-Latent Frequency-Time Modeling in Lightweight Acoustic Echo Cancellation
18. Efficient Audio Enhancement with a Differentiable Psychoacoustic Loss
19. Regularized Schrödinger Bridge via Distortion-Perception Perturbation for High-Fidelity Speech Enhancement
20. AnyBand: Unified Multi-Bandwidth Speech Extension via Frequency-Aware In-Context Spectral Infilling