Textraction: Unified Text-Guided Speaker Extraction and Enhancement for Single- and Multi-Channel Audio
cs.SD
Submitted: 2026-11-09
Updated: 2026-11-09
Project page: https://aviad3189.github.io/Textraction
Terminology
Sources
- SPMamba: State-space model is all you need in speech separation
- End-to-End DOA-Guided Speech Extraction in Noisy Multi-Talker Scenarios
- Binaural Target Speaker Extraction using Individualized HRTF
- Target Speech Diarization with Multimodal Prompts
- pTSE-T: Presentation Target Speaker Extraction using Unaligned Text Cues
- SAM Audio: Segment Anything in Audio
- Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction
- Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience
- Spatially-Guided Speaker Extraction Based on Relative Position Cues
- Gemma 3 Technical Report
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
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