1 code implementation • insights (ACL) 2022 • Philipp Koch, Matthias Aßenmacher, Christian Heumann
Evaluating generated text received new attention with the introduction of model-based metrics in recent years.
no code implementations • 3 Oct 2023 • Viktor Stojkoski, Philipp Koch, Eva Coll, Cesar A. Hidalgo
Despite global efforts to harmonize international trade statistics, our understanding of digital trade and its implications remains elusive.
no code implementations • 18 Aug 2023 • Philipp Koch, Gilary Vera Nuñez, Esteban Garces Arias, Christian Heumann, Matthias Schöffel, Alexander Häberlin, Matthias Aßenmacher
This dictionary entails record cards referring to lemmas in medieval Latin, a low-resource language.
1 code implementation • 12 Jan 2023 • Cem Akkus, Luyang Chu, Vladana Djakovic, Steffen Jauch-Walser, Philipp Koch, Giacomo Loss, Christopher Marquardt, Marco Moldovan, Nadja Sauter, Maximilian Schneider, Rickmer Schulte, Karol Urbanczyk, Jann Goschenhofer, Christian Heumann, Rasmus Hvingelby, Daniel Schalk, Matthias Aßenmacher
This book is the result of a seminar in which we reviewed multimodal approaches and attempted to create a solid overview of the field, starting with the current state-of-the-art approaches in the two subfields of Deep Learning individually.
1 code implementation • 9 Jan 2023 • Huy Phan, Kristian P. Lorenzen, Elisabeth Heremans, Oliver Y. Chén, Minh C. Tran, Philipp Koch, Alfred Mertins, Mathias Baumert, Kaare Mikkelsen, Maarten De Vos
In this work, we show that while encoding the logic of a whole sleep cycle is crucial to improve sleep staging performance, the sequential modelling approach in existing state-of-the-art deep learning models are inefficient for that purpose.
no code implementations • 28 Oct 2022 • Philipp Koch, Viktor Stojkoski, César A. Hidalgo
grows with both, the presence of immigrants with knowledge on that activity and immigrants with knowledge in related activities.
no code implementations • 17 Sep 2022 • Viktor Stojkoski, Philipp Koch, César A. Hidalgo
To achieve inclusive green growth, countries need to consider a multiplicity of economic, social, and environmental factors.
no code implementations • 29 Jan 2022 • Huy Phan, Thi Ngoc Tho Nguyen, Philipp Koch, Alfred Mertins
The network is composed of a backbone subnet and multiple task-specific subnets.
no code implementations • 23 May 2021 • Huy Phan, Kaare Mikkelsen, Oliver Y. Chén, Philipp Koch, Alfred Mertins, Maarten De Vos
It is based on the transformer backbone and offers interpretability of the model's decisions at both the epoch and sequence level.
no code implementations • 3 Mar 2021 • Huy Phan, Huy Le Nguyen, Oliver Y. Chén, Lam Pham, Philipp Koch, Ian McLoughlin, Alfred Mertins
The learned embedding in the subnetworks are then concatenated to form the multi-view embedding for classification similar to a simple concatenation network.
1 code implementation • 18 Oct 2020 • Huy Phan, Huy Le Nguyen, Oliver Y. Chén, Philipp Koch, Ngoc Q. K. Duong, Ian McLoughlin, Alfred Mertins
Existing generative adversarial networks (GANs) for speech enhancement solely rely on the convolution operation, which may obscure temporal dependencies across the sequence input.
no code implementations • 11 Sep 2020 • Huy Phan, Lam Pham, Philipp Koch, Ngoc Q. K. Duong, Ian McLoughlin, Alfred Mertins
Audio event localization and detection (SELD) have been commonly tackled using multitask models.
1 code implementation • 8 Jul 2020 • Huy Phan, Oliver Y. Chén, Minh C. Tran, Philipp Koch, Alfred Mertins, Maarten De Vos
This work proposes a sequence-to-sequence sleep staging model, XSleepNet, that is capable of learning a joint representation from both raw signals and time-frequency images.
Ranked #1 on Sleep Stage Detection on PhysioNet Challenge 2018
no code implementations • 23 Apr 2020 • Huy Phan, Kaare Mikkelsen, Oliver Y. Chén, Philipp Koch, Alfred Mertins, Preben Kidmose, Maarten De Vos
We employ the pretrained SeqSleepNet (i. e. the subject independent model) as a starting point and finetune it with the single-night personalization data to derive the personalized model.
2 code implementations • 15 Jan 2020 • Huy Phan, Ian V. McLoughlin, Lam Pham, Oliver Y. Chén, Philipp Koch, Maarten De Vos, Alfred Mertins
The former constrains the generators to learn a common mapping that is iteratively applied at all enhancement stages and results in a small model footprint.
1 code implementation • 30 Jul 2019 • Huy Phan, Oliver Y. Chén, Philipp Koch, Zongqing Lu, Ian McLoughlin, Alfred Mertins, Maarten De Vos
We employ the Montreal Archive of Sleep Studies (MASS) database consisting of 200 subjects as the source domain and study deep transfer learning on three different target domains: the Sleep Cassette subset and the Sleep Telemetry subset of the Sleep-EDF Expanded database, and the Surrey-cEEGrid database.
Ranked #1 on Multimodal Sleep Stage Detection on Surrey-PSG
Automatic Sleep Stage Classification Multimodal Sleep Stage Detection +2
no code implementations • 11 Apr 2019 • Huy Phan, Oliver Y. Chén, Philipp Koch, Alfred Mertins, Maarten De Vos
This work presents a deep transfer learning approach to overcome the channel mismatch problem and transfer knowledge from a large dataset to a small cohort to study automatic sleep staging with single-channel input.
no code implementations • 6 Apr 2019 • Huy Phan, Oliver Y. Chén, Lam Pham, Philipp Koch, Maarten De Vos, Ian McLoughlin, Alfred Mertins
Acoustic scenes are rich and redundant in their content.
no code implementations • 2 Nov 2018 • Huy Phan, Oliver Y. Chén, Philipp Koch, Lam Pham, Ian McLoughlin, Alfred Mertins, Maarten De Vos
We propose a multi-label multi-task framework based on a convolutional recurrent neural network to unify detection of isolated and overlapping audio events.
no code implementations • 2 Nov 2018 • Huy Phan, Oliver Y. Chén, Philipp Koch, Lam Pham, Ian McLoughlin, Alfred Mertins, Maarten De Vos
Moreover, as model fusion with deep network ensemble is prevalent in audio scene classification, we further study whether, and if so, when model fusion is necessary for this task.
no code implementations • 6 Dec 2017 • Huy Phan, Philipp Koch, Ian McLoughlin, Alfred Mertins
The proposed system consists of a novel inference step coupled with dual parallel tailored-loss deep neural networks (DNNs).
no code implementations • 14 Mar 2017 • Huy Phan, Philipp Koch, Fabrice Katzberg, Marco Maass, Radoslaw Mazur, Alfred Mertins
We introduce in this work an efficient approach for audio scene classification using deep recurrent neural networks.
no code implementations • 8 Jul 2016 • Huy Phan, Lars Hertel, Marco Maass, Philipp Koch, Alfred Mertins
The regression phase is then carried out to let the positive audio segments vote for the event onsets and offsets, and therefore model the temporal structure of audio events.
no code implementations • 8 Jul 2016 • Huy Phan, Lars Hertel, Marco Maass, Philipp Koch, Alfred Mertins
This category taxonomy is then used in the feature extraction step in which an audio scene instance is represented by a label tree embedding image.
no code implementations • 25 Jun 2016 • Huy Phan, Lars Hertel, Marco Maass, Philipp Koch, Alfred Mertins
We present in this paper an efficient approach for acoustic scene classification by exploring the structure of class labels.