LEAF: A learnable frontend for audio classification

N Zeghidour, O Teboul, FDC Quitry…�- arXiv preprint arXiv�…, 2021 - arxiv.org
Mel-filterbanks are fixed, engineered audio features which emulate human perception and
have been used through the history of audio understanding up to today. However, their�…
Save Cite Cited by 151 Related articles View as HTML

LEAF: A Learnable Frontend for Audio Classification

N Zeghidour, O Teboul, F de Chaumont Quitry…�- …�Conference on Learning�… - openreview.net
Mel-filterbanks are fixed, engineered audio features which emulate human perception and
have been used through the history of audio understanding up to today. However, their�…
Cite

LEAF: A Learnable Frontend for Audio Classification

N Zeghidour, O Teboul, F de Chaumont Quitry…�- arXiv e�…, 2021 - ui.adsabs.harvard.edu
Mel-filterbanks are fixed, engineered audio features which emulate human perception and
have been used through the history of audio understanding up to today. However, their�…
Cite