Latest Research in Sound
173 research papers · 2026 median publication year
Top Research Topics in Sound
- Sound — 90 papers
- Audio and Speech Processing — 21 papers
- Music and Audio Processing — 18 papers
- Computer Vision and Pattern Recognition — 6 papers
- Computation and Language — 5 papers
- Topic Modeling — 4 papers
- Music Technology and Sound Studies — 4 papers
- Signal Processing — 3 papers
- Machine Learning — 3 papers
- Diverse Music Education Insights — 2 papers
Highest-Cited Papers
- Helping Music Co-Creation Agents 'Listen' Well: Hierarchical Self-Supervised World Models for Understanding and Generation
- AudioScape-TTA: A Structured Soundscape Benchmark for Fine-Grained Text-to-Audio Evaluation
- Visual Representation Matters: Exploiting Temporal Differences in Video-to-Audio Generation
- A Dual Evaluation for Music Transcription
- Towards Robust Version Identification in the Wild: A Dataset, Benchmark, and Fine-Tuning Study
- Masked diffusion enables coherent beat tracking
- P-MUSE: Prompt-MIDI-Optional Model for Unified Instrumental Music Synthesis and Editing
- MAGENTA: Magnitude and Geometry-Enhanced Training Approach for Long-Tailed Sound Event Localization and Detection
- On the Geometry of Music Bandwidth Extension in Latent Spaces of Audio Codecs
- Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation
- InvFlowFD: Reference-Free and Background-Set-Free Perceptual Music Quality Metric with Flow Matching Inversion
- Calliphony: A Calligraphy-Driven Interface for Real-Time Generative Music Performance
- Learning Music Style for Piano Arrangement Through Cross-Modal Bootstrapping
- MIDI-LLM: Improving Text-to-MIDI Music Generation via Adapting Large Language Models
- SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks
- Multi-Task Multi-Frame Visual Piano Transcription
- DDSynth-RL: Audio Synthesizer Inversion via Discrete Diffusion with Reinforcement Learning
- AI-Based Sound Effect Generation: A Narrative Review of Generative Models Across Input Modalities
- Equivariant Music Transformer
- CLASVS: Continuous-Latent Autoregression for Melody-Preserving Lyric Editing in Singing Voice Synthesis