[ICML2026] SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
Xiaoyu Yang
marcoyang
AI & ML interests
ASR, Machine learning
Recent Activity
updated a model about 14 hours ago
marcoyang/SALMONN-2-8B published a model 11 days ago
marcoyang/SALMONN-2-8B updated a model about 1 month ago
marcoyang/spear-xlarge-speech-audioOrganizations
models 51
marcoyang/SALMONN-2-8B
Feature Extraction • 9B • Updated • 70
marcoyang/spear-xlarge-speech-audio
Feature Extraction • 0.6B • Updated • 23.3k • 7
marcoyang/spear-xlarge-speech-audio-v2
Feature Extraction • 0.6B • Updated • 256 • 2
marcoyang/spear-xlarge-speech-audio-v2-icefall
Updated
marcoyang/spear-base-speech-audio-v2
93.3M • Updated • 3.49k
marcoyang/spear-base-speech-v2
93.3M • Updated • 118
marcoyang/spear-base-speech-audio
93.3M • Updated • 3 • 2
marcoyang/spear-base-speech
93.3M • Updated • 1.88k
marcoyang/spear-large-speech-audio
0.3B • Updated • 7.3k
marcoyang/spear-large-speech
0.3B • Updated • 54 • 1