[ICML2026] SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
Xiaoyu Yang
marcoyang
AI & ML interests
ASR, Machine learning
Recent Activity
upvoted a paper 3 days ago
SPEAR: A Unified SSL Framework for Learning Speech and Audio
Representations updated a dataset 8 days ago
marcoyang/spear_code_librispeech published a dataset 8 days ago
marcoyang/spear_code_librispeechOrganizations
models 51
marcoyang/SALMONN-2-8B
Feature Extraction • 9B • Updated • 1.03k • 3
marcoyang/spear-xlarge-speech-audio
Feature Extraction • 0.6B • Updated • 356 • 7
marcoyang/spear-xlarge-speech-audio-v2
Feature Extraction • 0.6B • Updated • 976 • 6
marcoyang/spear-xlarge-speech-audio-v2-icefall
Updated
marcoyang/spear-base-speech-audio-v2
93.3M • Updated • 1.35k
marcoyang/spear-base-speech-v2
93.3M • Updated • 68
marcoyang/spear-base-speech-audio
93.3M • Updated • 21 • 2
marcoyang/spear-base-speech
93.3M • Updated • 349
marcoyang/spear-large-speech-audio
0.3B • Updated • 24.6k
marcoyang/spear-large-speech
0.3B • Updated • 66 • 1