🔄 In a Training Loop

Kai Li PRO

JusperLee

19 32 35

https://cslikai.cn

JusperLee

AI & ML interests

None yet

Recent Activity

upvoted a paper 15 days ago

Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

submitted a paper 15 days ago

Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

updated a Space 15 days ago

JusperLee/Falcon-Studio

View all activity

Organizations

None yet

Collections 1

Papers 11

spaces 5

Falcon Studio

🦅

Audio-visual target speaker extraction in your browser

DBS Listening Studio

🎧

Separate audio or video into speech, music, and sound‑effects stems

BEAVER

🦫

Training-Free Hierarchical Prompt Compression

Hive

🎵

Text-queried USS using AudioSep & FlowSep trained on HIVE.

Dolphin: Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention

👀

Separate and isolate individual speakers from videos

models 21

datasets 12

JusperLee/RealSSA-Real

Viewer • Updated 15 days ago • 54 • 425 • 3

JusperLee/RealSSA-Sim

Preview • Updated 15 days ago • 1.25k • 4

JusperLee/EchoSet

Viewer • Updated 28 days ago • 82.1k • 240 • 10

JusperLee/Hive-ALL

Viewer • Updated May 26 • 8.4M • 2.1k • 1

JusperLee/Hive

Viewer • Updated May 19 • 5.6M • 88 • 2

JusperLee/AudioTrust

Viewer • Updated Jul 10, 2025 • 8.1k • 458 • 7

JusperLee/Apollo-val-test-data

Updated Mar 7, 2025 • 13

JusperLee/SonicSet-v2

Updated Jan 22, 2025 • 139 • 6

JusperLee/LibriSpace

Updated Jul 23, 2024 • 6

JusperLee/LRS3-2Mix

Updated Feb 20, 2024 • 17

View 12 datasets