[ICML2026] SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
Xiaoyu Yang
marcoyang
AI & ML interests
ASR, Machine learning
Organizations
models 51
marcoyang/SALMONN-2-8B
Feature Extraction • 9B • Updated • 589 • 3
marcoyang/spear-xlarge-speech-audio
Feature Extraction • 0.6B • Updated • 549 • 7
marcoyang/spear-xlarge-speech-audio-v2
Feature Extraction • 0.6B • Updated • 696 • 6
marcoyang/spear-xlarge-speech-audio-v2-icefall
Updated
marcoyang/spear-base-speech-audio-v2
93.3M • Updated • 720
marcoyang/spear-base-speech-v2
93.3M • Updated • 67
marcoyang/spear-base-speech-audio
93.3M • Updated • 14 • 2
marcoyang/spear-base-speech
93.3M • Updated • 129
marcoyang/spear-large-speech-audio
0.3B • Updated • 256
marcoyang/spear-large-speech
0.3B • Updated • 60 • 1