Jan Schlüter, Gerald Gutenbrunner,
"EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use"
: Proceedings of the 30th European Signal Processing Conference (EUSIPCO), 9-2022
Original Titel:
EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use
Sprache des Titels:
Englisch
Original Buchtitel:
Proceedings of the 30th European Signal Processing Conference (EUSIPCO)
Original Kurzfassung:
In audio classification, differentiable auditory filterbanks with few
parameters cover the middle ground between hard-coded spectrograms and
raw audio. LEAF, a Gabor-based filterbank combined with Per-Channel
Energy Normalization (PCEN), has shown promising results, but is
computationally expensive. With inhomogeneous convolution kernel sizes
and strides, and by replacing PCEN with better parallelizable
operations, we can reach similar results more efficiently. In
experiments on six audio classification tasks, our frontend matches the
accuracy of LEAF at 3% of the cost, but both fail to consistently
outperform a fixed mel filterbank. The quest for learnable audio
frontends is not solved.
Forschungs-