[ICML2026] SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
Xiaoyu Yang
marcoyang
AI & ML interests
ASR, Machine learning
Recent Activity
liked a model 1 day ago
marcoyang/spear-xlarge-speech-audio-v2 published a dataset 3 days ago
marcoyang/easy_english_dataset updated a dataset 3 days ago
marcoyang/easy_english_datasetOrganizations
models 51
marcoyang/SALMONN-2-8B
Feature Extraction • 9B • Updated • 1k • 3
marcoyang/spear-xlarge-speech-audio
Feature Extraction • 0.6B • Updated • 2.39k • 7
marcoyang/spear-xlarge-speech-audio-v2
Feature Extraction • 0.6B • Updated • 1.71k • 10
marcoyang/spear-xlarge-speech-audio-v2-icefall
Updated
marcoyang/spear-base-speech-audio-v2
93.3M • Updated • 1.23k
marcoyang/spear-base-speech-v2
93.3M • Updated • 43
marcoyang/spear-base-speech-audio
93.3M • Updated • 11 • 2
marcoyang/spear-base-speech
93.3M • Updated • 111
marcoyang/spear-large-speech-audio
0.3B • Updated • 260
marcoyang/spear-large-speech
0.3B • Updated • 46 • 1