221 citations · 306 across the 21 of their papers we have counts for
5 papers · 1 filter
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models
Florian Schmid, Khaled Koutini, Gerhard Widmer
The introduction of large-scale audio datasets, such as AudioSet, paved the way for Transformers to conquer the audio domain and replace CNNs as the state-of-the-art neural network…
Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets
Paul Primus, Khaled Koutini, Gerhard Widmer
This work presents a text-to-audio-retrieval system based on pre-trained text and spectrogram transformers. Our method projects recordings and textual descriptions into a shared au…
Device-Robust Acoustic Scene Classification via Impulse Response Augmentation
Tobias Morocutti, Florian Schmid, Khaled Koutini +1
The ability to generalize to a wide range of recording devices is a crucial performance factor for audio classification models. The characteristics of different types of microphone…
Domain Information Control at Inference Time for Acoustic Scene Classification
Shahed Masoudian, Khaled Koutini, Markus Schedl +2
Domain shift is considered a challenge in machine learning as it causes significant degradation of model performance. In the Acoustic Scene Classification task (ASC), domain shift…
Low-Complexity Audio Embedding Extractors
Florian Schmid, Khaled Koutini, Gerhard Widmer
Solving tasks such as speaker recognition, music classification, or semantic audio event tagging with deep learning models typically requires computationally demanding networks. Ge…