AudioSphere: Towards Self-Supervised Spatial Audio Representation Models
cs.SD, cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/labhamlet/AudioSphere
Terminology
Sources
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
- w2v-SELD: A Sound Event Localization and Detection Framework for Self-Supervised Spatial Audio Pre-Training
- SHroom: A Python Framework for Ambisonics Room Acoustics Simulation and Binaural Rendering
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Beyond Omnidirectional: Neural Ambisonics Encoding for Arbitrary Microphone Directivity Patterns using Cross-Attention
- Sci-Phi: A Large Language Model Spatial Audio Descriptor
- Decoupled Weight Decay Regularization
- STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events
- ACCDOA: Activity-Coupled Cartesian Direction of Arrival Representation for Sound Event Localization and Detection
- Can Large Language Models Understand Spatial Audio?
- Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems