task · first seen 5 Oct 2026
speech separation
Also: stems, vocal removal, stem separation, AI vocal removal, source separation
Separating individual speaker signals from a mixed audio recording.
Mentions per week
PapersCodeDiscussion
Rank 176 on 2 Nov 2026 · 8 mentions in 28 days · 8 independent groups · papers → code · first seen 4 weeks ago · acceleration -0.29
Earliest sources
- SEAL: Mixture-Closed Additive Reconstruction and Refinement-Aware Expert Routing for Efficient Speech SeparationPapers · 5 Oct 2026 · Shao-Chun Hu, Zi-Xiang Lin, Jeih-Weih Hung, Hung-Shin Lee
- lvxworld/lux-in-musicCode · 8 Oct 2026 · lvxworld · 45 stars
- beneaze/ClubCraftCode · 14 Oct 2026 · beneaze · 35 stars
- Beyond Two Tracks: Speaker-Anchored Full-Duplex Dialogue RecoveryPapers · 19 Oct 2026 · Yuxuan Chen, Yang Xiao, Jack Sun, Chak Sun, Brick Li, Sam
- SLM-SS: Token-Based Speech Separation with Speech Language ModelsPapers · 20 Oct 2026 · Chenda Li, Tianhua Li, Yiming Chen, Wei Wang, Jiahe Wang, Xin Zhou, Yanmin Qian
- audioshake/audioshake-pythonCode · 21 Oct 2026 · audioshake · 25 stars
Latest sources
- Kezek: Splitting Mono Two-Person Conversations into Per-Speaker Tracks for Full-Duplex Dialogue DataPapers · 12 Nov 2026 · Bagzhan Karl, Alizhan Karl
- SPDMX: Large-Scale Open Stem Audio From Symbolic MusicPapers · 6 Nov 2026 · Phillip Long, Eduardo Escoto, Julian McAuley, Zachary Novack
- Junhua9981/LocalKTVCode · 3 Nov 2026 · Junhua9981 · 25 stars
- Cd1s/EngineX-OSCode · 1 Nov 2026 · Cd1s · 89 stars
- higurashi-ai/FastDialogueSidonCode · 26 Oct 2026 · higurashi-ai · 35 stars
- suitux/BackspnCode · 25 Oct 2026 · suitux · 23 stars
- audioshake/audioshake-pythonCode · 21 Oct 2026 · audioshake · 25 stars
- SLM-SS: Token-Based Speech Separation with Speech Language ModelsPapers · 20 Oct 2026 · Chenda Li, Tianhua Li, Yiming Chen, Wei Wang, Jiahe Wang, Xin Zhou, Yanmin Qian
- Beyond Two Tracks: Speaker-Anchored Full-Duplex Dialogue RecoveryPapers · 19 Oct 2026 · Yuxuan Chen, Yang Xiao, Jack Sun, Chak Sun, Brick Li, Sam
- beneaze/ClubCraftCode · 14 Oct 2026 · beneaze · 35 stars
- lvxworld/lux-in-musicCode · 8 Oct 2026 · lvxworld · 45 stars
- SEAL: Mixture-Closed Additive Reconstruction and Refinement-Aware Expert Routing for Efficient Speech SeparationPapers · 5 Oct 2026 · Shao-Chun Hu, Zi-Xiang Lin, Jeih-Weih Hung, Hung-Shin Lee