Audio transformers: Transformer architectures for large scale audio understanding. adieu convolutions
P Verma, J Berger�- arXiv preprint arXiv:2105.00335, 2021 - arxiv.org
Over the past two decades, CNN architectures have produced compelling models of sound
perception and cognition, learning hierarchical organizations of features. Analogous to�…
perception and cognition, learning hierarchical organizations of features. Analogous to�…
Raw waveform-based audio classification using sample-level CNN architectures
Music, speech, and acoustic scene sound are often handled separately in the audio domain
because of their different signal characteristics. However, as the image domain grows�…
because of their different signal characteristics. However, as the image domain grows�…
Rethinking CNN models for audio classification
In this paper, we show that ImageNet-Pretrained standard deep CNN models can be used
as strong baseline networks for audio classification. Even though there is a significant�…
as strong baseline networks for audio classification. Even though there is a significant�…
End-to-end audio strikes back: Boosting augmentations towards an efficient audio classification network
While efficient architectures and a plethora of augmentations for end-to-end image
classification tasks have been suggested and heavily investigated, state-of-the-art�…
classification tasks have been suggested and heavily investigated, state-of-the-art�…
Aclnet: efficient end-to-end audio classification cnn
JJ Huang, JJA Leanos�- arXiv preprint arXiv:1811.06669, 2018 - arxiv.org
We propose an efficient end-to-end convolutional neural network architecture, AclNet, for
audio classification. When trained with our data augmentation and regularization, we�…
audio classification. When trained with our data augmentation and regularization, we�…
Ast: Audio spectrogram transformer
In the past decade, convolutional neural networks (CNNs) have been widely adopted as the
main building block for end-to-end audio classification models, which aim to learn a direct�…
main building block for end-to-end audio classification models, which aim to learn a direct�…
Receptive field regularization techniques for audio classification and tagging with deep convolutional neural networks
K Koutini, H Eghbal-zadeh…�- IEEE/ACM Transactions�…, 2021 - ieeexplore.ieee.org
In this paper, we study the performance of variants of well-known Convolutional Neural
Network (CNN) architectures on different audio tasks. We show that tuning the Receptive�…
Network (CNN) architectures on different audio tasks. We show that tuning the Receptive�…
Tiny transformers for environmental sound classification at the edge
With the growth of the Internet of Things and the rise of Big Data, data processing and
machine learning applications are being moved to cheap and low size, weight, and power�…
machine learning applications are being moved to cheap and low size, weight, and power�…
Randomly weighted cnns for (music) audio classification
The computer vision literature shows that randomly weighted neural networks perform
reasonably as feature extractors. Following this idea, we study how non-trained (randomly�…
reasonably as feature extractors. Following this idea, we study how non-trained (randomly�…
Comparison and analysis of SampleCNN architectures for audio classification
End-to-end learning with convolutional neural networks (CNNs) has become a standard
approach in image classification. However, in audio classification, CNN-based models that�…
approach in image classification. However, in audio classification, CNN-based models that�…