[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 4 days ago
marcoyang/spear_code_librispeech published a dataset 4 days ago
marcoyang/spear_code_librispeech updated a model 3 months ago
marcoyang/SALMONN-2-8BOrganizations
models 51
marcoyang/SALMONN-2-8B
Feature Extraction • 9B • Updated • 950 • 3
marcoyang/spear-xlarge-speech-audio
Feature Extraction • 0.6B • Updated • 509 • 7
marcoyang/spear-xlarge-speech-audio-v2
Feature Extraction • 0.6B • Updated • 959 • 6
marcoyang/spear-xlarge-speech-audio-v2-icefall
Updated
marcoyang/spear-base-speech-audio-v2
93.3M • Updated • 1.27k
marcoyang/spear-base-speech-v2
93.3M • Updated • 74
marcoyang/spear-base-speech-audio
93.3M • Updated • 22 • 2
marcoyang/spear-base-speech
93.3M • Updated • 311
marcoyang/spear-large-speech-audio
0.3B • Updated • 19.6k
marcoyang/spear-large-speech
0.3B • Updated • 68 • 1