221 citations · 306 across the 21 of their papers we have counts for
21 papers
Woosh: A Sound Effects Foundation Model
Gaëtan Hadjeres, Marc Ferras, Khaled Koutini +7
The audio research community depends on open generative models as foundational tools for building novel approaches and establishing baselines. In this report, we present Woosh, Son…
Creating a Good Teacher for Knowledge Distillation in Acoustic Scene Classification
Tobias Morocutti, Florian Schmid, Khaled Koutini +1
Knowledge Distillation (KD) is a widespread technique for compressing the knowledge of large models into more compact and efficient models. KD has proved to be highly effective in…
Data-Efficient Low-Complexity Acoustic Scene Classification in the DCASE 2024 Challenge
Florian Schmid, Paul Primus, Toni Heittola +4
This article describes the Data-Efficient Low-Complexity Acoustic Scene Classification Task in the DCASE 2024 Challenge and the corresponding baseline system. The task setup is a c…
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…
Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers
Khaled Koutini, Shahed Masoudian, Florian Schmid +3
The success of supervised deep learning methods is largely due to their ability to learn relevant features from raw data. Deep Neural Networks (DNNs) trained on large-scale dataset…
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation
Florian Schmid, Khaled Koutini, Gerhard Widmer
Audio Spectrogram Transformer models rule the field of Audio Tagging, outrunning previously dominating Convolutional Neural Networks (CNNs). Their superiority is based on the abili…
Efficient Training of Audio Transformers with Patchout
Khaled Koutini, Jan Schlüter, Hamid Eghbal-zadeh +1
The great success of transformer-based models in natural language processing (NLP) has led to various attempts at adapting these architectures to other domains such as vision and a…
Over-Parameterization and Generalization in Audio Classification
Khaled Koutini, Hamid Eghbal-zadeh, Florian Henkel +2
Convolutional Neural Networks (CNNs) have been dominating classification tasks in various domains, such as machine vision, machine listening, and natural language processing. In ma…
Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks
Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer
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 Field…
Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping
Khaled Koutini, Florian Henkel, Hamid Eghbal-zadeh +1
Deep Neural Networks are known to be very demanding in terms of computing and memory requirements. Due to the ever increasing use of embedded systems and mobile devices with a limi…
Receptive-Field Regularized CNNs for Music Classification and Tagging
Khaled Koutini, Hamid Eghbal-Zadeh, Verena Haunschmid +3
Convolutional Neural Networks (CNNs) have been successfully used in various Music Information Retrieval (MIR) tasks, both as end-to-end models and as feature extractors for more co…
On Data Augmentation and Adversarial Risk: An Empirical Analysis
Hamid Eghbal-zadeh, Khaled Koutini, Paul Primus +5
Data augmentation techniques have become standard practice in deep learning, as it has been shown to greatly improve the generalisation abilities of models. These techniques rely o…
Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs
Khaled Koutini, Shreyan Chowdhury, Verena Haunschmid +2
We present CP-JKU submission to MediaEval 2019; a Receptive Field-(RF)-regularized and Frequency-Aware CNN approach for tagging music with emotion/mood labels. We perform an invest…
Receptive-field-regularized CNN variants for acoustic scene classification
Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer
Acoustic scene classification and related tasks have been dominated by Convolutional Neural Networks (CNNs). Top-performing CNNs use mainly audio spectograms as input and borrow th…
Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification
Paul Primus, Hamid Eghbal-zadeh, David Eitelsebner +3
Distribution mismatches between the data seen at training and at application time remain a major challenge in all application areas of machine learning. We study this problem in th…
The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification
Khaled Koutini, Hamid Eghbal-zadeh, Matthias Dorfer +1
Convolutional Neural Networks (CNNs) have had great success in many machine vision as well as machine audition tasks. Many image recognition network architectures have consequently…
Deep SNP: An End-to-end Deep Neural Network with Attention-based Localization for Break-point Detection in SNP Array Genomic data
Hamid Eghbal-zadeh, Lukas Fischer, Niko Popitsch +9
Diagnosis and risk stratification of cancer and many other diseases require the detection of genomic breakpoints as a prerequisite of calling copy number alterations (CNA). This, h…