[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 5 days ago
marcoyang/salmonn-2-8b-test published a model 9 days ago
marcoyang/salmonn-2-8b-test updated a model 29 days ago
marcoyang/spear-xlarge-speech-audioOrganizations
models 51
marcoyang/salmonn-2-8b-test
Feature Extraction • 9B • Updated • 70
marcoyang/spear-xlarge-speech-audio
Feature Extraction • 0.6B • Updated • 25.7k • 7
marcoyang/spear-xlarge-speech-audio-v2
Feature Extraction • 0.6B • Updated • 237 • 2
marcoyang/spear-xlarge-speech-audio-v2-icefall
Updated
marcoyang/spear-base-speech-audio-v2
93.3M • Updated • 3.35k
marcoyang/spear-base-speech-v2
93.3M • Updated • 89
marcoyang/spear-base-speech-audio
93.3M • Updated • 3 • 2
marcoyang/spear-base-speech
93.3M • Updated • 1.7k
marcoyang/spear-large-speech-audio
0.3B • Updated • 7.06k
marcoyang/spear-large-speech
0.3B • Updated • 31 • 1