Spatially-Guided Speaker Extraction Based on Relative Position Cues
cs.SD, eess.AS
Submitted: 2026-11-01
Updated: 2026-11-01
Project page: https://aviad3189.github.io/RPC-extraction
Terminology
Sources
- Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation
- TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation
- End-to-End DOA-Guided Speech Extraction in Noisy Multi-Talker Scenarios
- All Neural Low-latency Directional Speech Extraction
- End-to-End Multi-Microphone Speaker Extraction Using Relative Transfer Functions
- Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction
- Neural Spatio-Temporal Beamformer for Target Speech Separation
- Implicit Neural Spatial Filtering for Multichannel Source Separation in the Waveform Domain
- Distance-Based Sound Separation
- FiLM: Visual Reasoning with a General Conditioning Layer
- Decoupled Weight Decay Regularization
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