Latest Research in Sound

Top Research Topics in Sound

• Sound — 70 papers
• Music and Audio Processing — 15 papers
• Audio and Speech Processing — 13 papers
• Computer Vision and Pattern Recognition — 10 papers
• Multimedia — 2 papers
• Diverse Music Education Insights — 2 papers
• Human Motion and Animation — 2 papers
• Neuroscience and Music Perception — 2 papers
• Artificial Intelligence — 1 papers
• Human-Computer Interaction — 1 papers

Highest-Cited Papers

1. Expressive Dizi Synthesis: Unlimited Synthetic Datasets, Real–Synthetic Integration and Technique Labeling
2. MuseCritic: Learning Multi-Aspect Song Rewards through Natural-Language Aesthetic Critiques
3. Dialogue-Aware Video-to-Music Generation Using Public Domain Film Collections
4. HarmoniDPO: Video-guided Audio Generation via Preference-Optimized Diffusion
5. Classification of Assamese regional songs using a hybrid model of machine learning and deep learning
6. Plainchant music modeling through Zipf’s law
7. Beyond Dry References: Learning Relative Audio Effects Representations via Contrastive Distance Learning
8. A Dataset and Benchmark for Optical Music Recognition of String Quartet Scores
9. MAJEPPA: Morphing and Assessing in a Unified Piano Performance Space
10. Beyond Reconstruction: Full-Context Generative DiT for Music Generation
11. Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence
12. Pitch Contour Tokenization using VQ-VAE and Its Application on Korean Traditional Music Analysis
13. Qwen-MusicAVQA-7B: A Multimodal Model for Music Audio-Visual QA
14. CLASVS: Continuous-Latent Autoregression for Melody-Preserving Lyric Editing in Singing Voice Synthesis
15. AudioMap: Cloze-and-Choice Reinforcement Learning for Time-Aware Dense Audio Captioning
16. SonicWeave: Chunk-Routed Mixture-of-Experts for Unified Audio Scene Generation
17. RAG-Audio: Retrieval-Augmented Generation for Faithful Brain-to-Audio Reconstruction
18. MusicLayout: Explicit Structural Planning for Controllable Text-to-Music Generation
19. SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding
20. NBA_Streaming: A Large-Scale Benchmark for Fine-Grained Basketball Commentary Generation in Continuous Streams