Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models

1 code implementation • 24 Oct 2023 • Florian Schmid, Khaled Koutini, Gerhard Widmer

Audio Spectrogram Transformers are excellent at exploiting large datasets, creating powerful pre-trained models that surpass CNNs when fine-tuned on downstream tasks.

Audio Classification Audio Tagging +2

Device-Robust Acoustic Scene Classification via Impulse Response Augmentation

1 code implementation • 12 May 2023 • Tobias Morocutti, Florian Schmid, Khaled Koutini, Gerhard Widmer

However, we also show that DIR augmentation and Freq-MixStyle are complementary, achieving a new state-of-the-art performance on signals recorded by devices unseen during training.

Acoustic Scene Classification Audio Classification +1

Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers

1 code implementation • 25 Nov 2022 • Khaled Koutini, Shahed Masoudian, Florian Schmid, Hamid Eghbal-zadeh, Jan Schlüter, Gerhard Widmer

Furthermore, we will show that transformers trained on Audioset can be extremely effective representation extractors for a wide range of downstream tasks.

Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation

2 code implementations • 9 Nov 2022 • Florian Schmid, Khaled Koutini, Gerhard Widmer

We provide models of different complexity levels, scaling from low-complexity models up to a new state-of-the-art performance of . 483 mAP on AudioSet.

Audio Classification Audio Tagging +2