Latest Research in Sound
102 research papers · 2026 median publication year
Top Research Topics in Sound
- Sound — 59 papers
- Audio and Speech Processing — 11 papers
- Music and Audio Processing — 9 papers
- Computer Vision and Pattern Recognition — 8 papers
- Human Motion and Animation — 3 papers
- Human-Computer Interaction — 2 papers
- Multimedia — 2 papers
- Machine Learning — 1 papers
- Neuroscience and Music Perception — 1 papers
- Emotion and Mood Recognition — 1 papers
Highest-Cited Papers
- CustomDance: Customized 3D Dance Generation with Coarse-to-Fine Human-Centered Interactive Control
- Finetuning Strategies for Querying Sounds by Vocal Imitation
- Computational Features for Symbolic Melody Analysis
- Dance Movement Recognition and Analysis Based on Deep Learning and Fuzzy Control Algorithms
- Why GPT-Style Models Do Not Directly Transfer to Symbolic Music: Compression in the Wrong Coordinate System
- UniVerse: Benchmarking and Enhancing LALMs on Culturally Inclusive Low-Resource Music Understanding
- The Bregman Cue-Sensitivity Map: Auditory-Scene-Analysis Cues Across Music Foundation Models
- Machine learning of artistic fingerprints in jazz
- Automatic Transcription of Microtonal Free-Rhythm Vocal Music: A Case Study in Iranian Classical Music
- An affective computing framework for preschool music education using MoE architecture and neural radiance fields
- Efficient Audio-Visual Generation via Synchrony-Aware Cross-Modal Sparse Attention
- Whole-Piece Training for Symbolic Music Language Models via Full-Horizon Compressed Recurrence
- UOT-IR: Structured Routing of High-Polyphony Symbolic Music into Fixed-Budget Representations
- Sonalyzer-Moz: A Framework for Analyzing the Structure of Mozart's Sonata Form
- MusicLayout: Explicit Structural Planning for Controllable Text-to-Music Generation
- What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models
- ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling
- BAT: Learning to Reason about Spatial Sounds with Large Language Models
- SALSA-V: Shortcut-Augmented Long-form Synchronized Audio from Videos
- Expressive Dizi Synthesis: Unlimited Synthetic Datasets, Real–Synthetic Integration and Technique Labeling