[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 4 days ago
marcoyang/spear-xlarge-speech-audio updated a collection 4 days ago
SPEAR encoders updated a model 4 days ago
marcoyang/spear-xlarge-speech-audio-v2Organizations
models 50
marcoyang/spear-xlarge-speech-audio
Feature Extraction • 0.6B • Updated • 12.8k • 7
marcoyang/spear-xlarge-speech-audio-v2
Feature Extraction • 0.6B • Updated • 36
marcoyang/spear-xlarge-speech-audio-v2-icefall
Updated
marcoyang/spear-base-speech-audio-v2
93.3M • Updated • 383
marcoyang/spear-base-speech-v2
93.3M • Updated • 232
marcoyang/spear-base-speech-audio
93.3M • Updated • 10 • 2
marcoyang/spear-base-speech
93.3M • Updated • 93
marcoyang/spear-large-speech-audio
0.3B • Updated • 217
marcoyang/spear-large-speech
0.3B • Updated • 24 • 1
marcoyang/transformer-causal-600m-spear-speech
Updated