Khaled Koutini

Khaled Koutini

Auto-generated profile, based on publicly available information

Khaled Koutini

LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Linz, Austria

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 May 2021 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
KKKhaled Koutini
Khaled Koutini
HEHamid Eghbal-zadeh
Hamid Eghbal-zadeh
GWGerhard Widmer
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 (RF) of CNNs is crucial to their generalization. An insufficient RF limits the CNN's ability to fit the training data. In contrast, CNNs with an excessive RF tend to over-fit the training data and fail to generalize to unseen testing data. As state-of-the-art CNN architectures - in computer vision and other domains - tend to go deeper in terms of number of layers, their RF size increases and therefore they degrade in performance in several audio classification and tagging tasks. We study well-known CNN architectures and how their building blocks affect their receptive field. We propose several systematic approaches to control the RF of CNNs and systematically test the resulting architectures on different audio classification and tagging tasks and datasets. The experiments show that regularizing the RF of CNNs using our proposed approaches can drastically improve the generalization of models, out-performing complex architectures and pre-trained models on larger datasets. The proposed CNNs achieve state-of-the-art results in multiple tasks, from acoustic scene classification to emotion and theme detection in music to instrument recognition, as demonstrated by top ranks in several pertinent challenges (DCASE, MediaEval).

18 March 2024 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Open access
FSFlorian Schmid
Florian Schmid
KKKhaled Koutini
Khaled Koutini
GWGerhard Widmer
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 architecture for many tasks. Audio Spectrogram Transformers are excellent at exploiting large datasets, creating powerful pre-trained models that surpass CNNs when fine-tuned on downstream tasks. However, current popular Audio Spectrogram Transformers are demanding in terms of computational complexity compared to CNNs. Recently, we have shown that, by employing Transformer-to-CNN Knowledge Distillation, efficient CNNs can catch up with and even outperform Transformers on large datasets. In this work, we extend this line of research and increase the capacity of efficient CNNs by introducing dynamic CNN blocks constructed of dynamic convolutions, a dynamic ReLU activation function, and Coordinate Attention. We show that these dynamic CNNs outperform traditional efficient CNNs, such as MobileNets, in terms of the performance–complexity trade-off at the task of audio tagging on the large-scale AudioSet. Our experiments further indicate that the proposed dynamic CNNs achieve competitive performance with Transformer-based models for end-to-end fine-tuning on downstream tasks while being much more computationally efficient.

6 November 2023 in Information Sciences
Verified
Journal Article
Closed access
HEHamid Eghbal-zadeh
Hamid Eghbal-zadeh
WZWerner Zellinger
Werner Zellinger
MPMaura Pintor
Maura Pintor
KGKathrin Grosse
Kathrin Grosse
KKKhaled Koutini
Khaled Koutini
GWGerhard Widmer
Gerhard Widmer