Cem Subakan's picture

Cem Subakan

cemsubakan

·

https://ycemsubakan.github.io/

ycemsubakan

AI & ML interests

Machine learning for audio, probabilistic machine learning

Recent Activity

updated a model about 3 hours ago

cemsubakan/my-checkpoint

published a model about 3 hours ago

cemsubakan/my-checkpoint

upvoted a paper 11 months ago

Discrete Audio Tokens: More Than a Survey!

View all activity

Organizations

updated a model about 3 hours ago

cemsubakan/my-checkpoint

Updated about 3 hours ago

published a model about 3 hours ago

cemsubakan/my-checkpoint

Updated about 3 hours ago

upvoted a paper 11 months ago

Discrete Audio Tokens: More Than a Survey!

Paper • 2506.10274 • Published Jun 12, 2025 • 32

New activity in speechbrain/sepformer-wsj03mix over 1 year ago

Source separation for multi-channel data

#1 opened over 1 year ago by

updated 8 models about 2 years ago

speechbrain/PIQ-ESC50

Updated Feb 25, 2024 • 61 • 3

speechbrain/cnn14-esc50

Updated Feb 25, 2024 • 102 • 3

speechbrain/sepformer-libri3mix

Audio-to-Audio • Updated Feb 25, 2024 • 286 • 7

speechbrain/sepformer-libri2mix

Audio-to-Audio • Updated Feb 25, 2024 • 706 • 9

speechbrain/sepformer-wham16k-enhancement

Audio-to-Audio • Updated Feb 25, 2024 • 8.87k • 32

speechbrain/sepformer-wham-enhancement

Audio-to-Audio • Updated Feb 25, 2024 • 91 • 33

speechbrain/sepformer-whamr-enhancement

Audio-to-Audio • Updated Feb 25, 2024 • 222 • 14

speechbrain/resepformer-wsj02mix

Audio-to-Audio • Updated Feb 25, 2024 • 354 • 4

New activity in speechbrain/sepformer-wham16k-enhancement about 2 years ago

Very different result with sepformer speech enhancement

#1 opened about 3 years ago by

liked a Space about 3 years ago

CryCeleb2023