EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use
In audio classification, differentiable auditory filterbanks with few parameters cover the middle ground between hard-coded spectrograms and raw audio. LEAF (arXiv:2101.08596), 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.
Code (1)
Tasks
Audio ClassificationClassificationInstrument RecognitionPitch ClassificationSpoken language identificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Universal Learnable Audio Frontend
Mel-filterbanks are fixed, engineered audio features which emulate human perception and have lived through the history of audio understanding up to today. However, their undeniable qualities are counterbalanced by the fu…
Audio ClassificationLEAF: A Learnable Frontend for Audio Classification
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 undeniable qualities are counterbalanced by th…
Audio ClassificationClassificationGeneral ClassificationLearnable Frontends that do not Learn: Quantifying Sensitivity to Filterbank Initialisation
While much of modern speech and audio processing relies on deep neural networks trained using fixed audio representations, recent studies suggest great potential in acoustic frontends learnt jointly with a backend. In th…
Action DetectionActivity DetectionSensitivityDeep Feature Learning for Medical Acoustics
The purpose of this paper is to compare different learnable frontends in medical acoustics tasks. A framework has been implemented to classify human respiratory sounds and heartbeats in two categories, i.e. healthy or af…
Audio ClassificationLearning neural audio features without supervision
Deep audio classification, traditionally cast as training a deep neural network on top of mel-filterbanks in a supervised fashion, has recently benefited from two independent lines of work. The first one explores "learna…
Audio ClassificationSelf-Supervised Learning