TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation
Kai Li PRO
JusperLee
AI & ML interests
None yet
Recent Activity
new activity about 3 hours ago
JusperLee/referential-dangling-detector:Add paper and project page links upvoted a paper about 14 hours ago
Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection upvoted a paper about 18 hours ago
Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt CompressionOrganizations
spaces 3
Sleeping
Agents
4
BEAVER
🦫
Training-Free Hierarchical Prompt Compression
Running on Zero
Agents
1
Hive
🎵
Text-queried USS using AudioSep & FlowSep trained on HIVE.
Running
Agents
6
Dolphin: Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention
👀
Separate and isolate individual speakers from videos
models 17
JusperLee/referential-dangling-detector
Text Classification • 0.1B • Updated • 35 • 2
JusperLee/Dolphin
Audio-to-Audio • 7.04M • Updated • 1.62k • 16
JusperLee/Real-World-AVSE-Baseline-Track2
Audio-to-Audio • 25M • Updated • 18
JusperLee/Real-World-AVSE-Baseline-Track1
Audio-to-Audio • 25M • Updated • 37
JusperLee/FlowSep-hive
Audio-to-Audio • Updated • 11
JusperLee/AudioSep-hive
Audio-to-Audio • Updated • 16
JusperLee/TIGER-speech-tiny
Audio-to-Audio • 102k • Updated • 121 • 2
JusperLee/TIGER-speech-small
Audio-to-Audio • 822k • Updated • 69 • 2
JusperLee/TIGER-speech
Audio-to-Audio • 822k • Updated • 15.3k • 24
JusperLee/TIGER-DnR
Audio-to-Audio • 4.22M • Updated • 115k • 23
datasets 10
JusperLee/Hive-ALL
Viewer • Updated • 8.4M • 600 • 1
JusperLee/Hive
Viewer • Updated • 5.6M • 65 • 1
JusperLee/AudioTrust
Viewer • Updated • 8.1k • 305 • 7
JusperLee/Apollo-val-test-data
Updated • 13
JusperLee/SonicSet-v2
Updated • 27 • 4
JusperLee/EchoSet
Viewer • Updated • 82.1k • 255 • 10
JusperLee/LibriSpace
Updated • 8
JusperLee/LRS3-2Mix
Updated • 12
JusperLee/VoxCeleb2-2Mix
Updated • 14 • 3
JusperLee/LRS2-2Mix
Updated • 53 • 7