[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 dataset about 15 hours ago
marcoyang/spear_code_librispeech published a dataset about 16 hours ago
marcoyang/spear_code_librispeech updated a model 2 months ago
marcoyang/SALMONN-2-8BOrganizations
models 51
marcoyang/SALMONN-2-8B
Feature Extraction • 9B • Updated • 911 • 3
marcoyang/spear-xlarge-speech-audio
Feature Extraction • 0.6B • Updated • 519 • 7
marcoyang/spear-xlarge-speech-audio-v2
Feature Extraction • 0.6B • Updated • 663 • 6
marcoyang/spear-xlarge-speech-audio-v2-icefall
Updated
marcoyang/spear-base-speech-audio-v2
93.3M • Updated • 1.1k
marcoyang/spear-base-speech-v2
93.3M • Updated • 80
marcoyang/spear-base-speech-audio
93.3M • Updated • 21 • 2
marcoyang/spear-base-speech
93.3M • Updated • 276
marcoyang/spear-large-speech-audio
0.3B • Updated • 507
marcoyang/spear-large-speech
0.3B • Updated • 66 • 1