Latest Research in Sound

Top Research Topics in Sound

• Sound — 36 papers
• Audio and Speech Processing — 28 papers
• Computation and Language — 6 papers
• Machine Learning — 3 papers
• Computer Vision and Pattern Recognition — 2 papers
• Speech and Audio Processing — 2 papers
• Hearing Loss and Rehabilitation — 1 papers
• Phonetics and Phonology Research — 1 papers
• Natural Language Processing Techniques — 1 papers
• Speech Recognition and Synthesis — 1 papers

Highest-Cited Papers

1. Speech intelligibility comparison of standalone and two-stage deep learning architectures for behind-the-ear-to-binaural enhancement
2. CircleMatch: Prototype Matching with Circular Temporal Statistics for Tiny Keyword Spotting
3. Soft Posterior Speaker Injection for Multi-Talker Speech Recognition
4. RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation
5. Mask-Based Speech Enhancement for Spatial Audio: A Comparison of Ambisonics, Beamforming, and Microphone Channels
6. GrainSpeech: Less Context, More Detail for Compact Speech Synthesis
7. G-Mamba: Sparse Graph-Guided Mamba for Audio-Visual Speech Enhancement
8. Task-Directed Residual AddUNet:Perfect-Reconstruction Routing for Full-Rate Representations
9. Performance and Complexity Trade-off Optimization of Speech Models During Training
10. LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs
11. Probing Layer-Wise Robustness and Sensitivity of Speech Enhancement Models
12. Directivity-Conditioned Low-Latency Neural Filtering for Speech Enhancement in Hearing Aids
13. Ring Mixing with Auxiliary Signal-to-Consistency-Error Ratio Loss for Unsupervised Denoising in Speech Separation
14. Exploiting Noise Inseparability for Weakly-Supervised Discriminative Speech Denoising Using Noisy Targets
15. Controllable Dysarthric Speech Synthesis with Patient-Specific Conditioning for Speaker-Diverse ASR Augmentation
16. Differentiable Digital Signal Processing Mixture Model-Guided Diffusion for Synthesis Parameter Estimation from Harmonic Sound Mixtures
17. DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis
18. DualSpecSE: A Dual-Path Speech Enhancement Network Integrating Mel and Complex Spectrograms
19. Head-Pose-Aware Visual Speech Recognition with FiLM Modulation
20. Location-based Training with Complementary Folded Linear Orderings for Multichannel Speech Separation