A Faster and Better Framework for Self-Supervised Speech Representation Learning
Yifan Yang
yfyeung
AI & ML interests
None yet
Recent Activity
authored a paper about 14 hours ago
WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling upvoted a paper 22 days ago
SPEAR: A Unified SSL Framework for Learning Speech and Audio
RepresentationsOrganizations
models 25
yfyeung/CLSP
0.7B • Updated • 1.61k • 2
yfyeung/icefall-asr-gigaspeech-zipformer-2025-07-15
Updated • 1
yfyeung/icefall-asr-gigaspeech2-th-zipformer-2024-06-20
Updated • 5
yfyeung/kmeans-librispeech-wavlm-base
Updated
yfyeung/spear-asr-librispeech
Updated
yfyeung/kmeans-librispeech-hubert-base
Updated
yfyeung/librispeech_test-clean_4-10s-cosyvoice2
Updated
yfyeung/librispeech_test-clean_4-10s-e2tts
Updated
yfyeung/librispeech_test-clean_4-10s-s3tokenizer-reconstruct
Updated
yfyeung/valle-libritts-pc-phone93
Updated
datasets 15
yfyeung/FCaps
Preview • Updated • 61 • 4
yfyeung/dataoceanai-arabic-raw
Preview • Updated • 2
yfyeung/gigaspeech-icefall-data
Viewer • Updated • 275M • 172
yfyeung/vi2000-icefall-data
Updated • 1
yfyeung/vctk
Viewer • Updated • 108 • 23
yfyeung/librispeech_test-clean_4-10s
Viewer • Updated • 2.47k • 89
yfyeung/libritts-s3tokenizer-v2-25hz
Viewer • Updated • 740k • 25
yfyeung/libritts-s3tokenizer-v1-50hz
Viewer • Updated • 740k • 16
yfyeung/libritts-encodec
Preview • Updated • 14
yfyeung/librilight-hubert-base-ls960-iter2-l9-km500
Viewer • Updated • 273k • 11