no code implementations • 2 Nov 2023 • Shubhr Singh, Christian J. Steinmetz, Emmanouil Benetos, Huy Phan, Dan Stowell
Deep learning models such as CNNs and Transformers have achieved impressive performance for end-to-end audio tagging.
no code implementations • 28 May 2023 • Jinhua Liang, Xubo Liu, Haohe Liu, Huy Phan, Emmanouil Benetos, Mark D. Plumbley, Wenwu Wang
We presented the Treff adapter, a training-efficient adapter for CLAP, to boost zero-shot classification performance by making use of a small set of labelled data.
no code implementations • 27 Mar 2023 • Konstantinos Kontras, Christos Chatzichristos, Huy Phan, Johan Suykens, Maarten De Vos
The results indicate that training the model on multimodal data does positively influence performance when tested on unimodal data.
no code implementations • 7 Mar 2023 • Dat Ngo, Lam Pham, Huy Phan, Minh Tran, Delaram Jarchi, Sefki Kolozali
Notably, we achieved the Top-1 performance in Task 2-1 and Task 2-2 with the highest Score of 74. 5% and 53. 9%, respectively.
no code implementations • 5 Feb 2023 • Jiachen Luo, Huy Phan, Joshua Reiss
Multimodal emotion recognition (MER) is a fundamental complex research problem due to the uncertainty of human emotional expression and the heterogeneity gap between different modalities.
no code implementations • 5 Feb 2023 • Jiachen Luo, Huy Phan, Joshua Reiss
Accurately detecting emotions in conversation is a necessary yet challenging task due to the complexity of emotions and dynamics in dialogues.
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 • 7 Dec 2022 • Ruchi Pandey, Shreyas Jaiswal, Huy Phan, Santosh Nannuru
In this paper, we do a comprehensive analysis of improvement in sound source localization by combining the direction of arrivals (DOAs) with their derivatives which quantify the changes in the positions of sources over time.
no code implementations • 4 Dec 2022 • Huy Phan, Miao Yin, Yang Sui, Bo Yuan, Saman Zonouz
Considering the co-importance of model compactness and robustness in practical applications, several prior works have explored to improve the adversarial robustness of the sparse neural networks.
no code implementations • 1 Nov 2022 • Marco Comunità, Christian J. Steinmetz, Huy Phan, Joshua D. Reiss
Deep learning approaches for black-box modelling of audio effects have shown promise, however, the majority of existing work focuses on nonlinear effects with behaviour on relatively short time-scales, such as guitar amplifiers and distortion.
no code implementations • 20 Sep 2022 • Oliver Y. Chén, Florian Lipsmeier, Huy Phan, Frank Dondelinger, Andrew Creagh, Christian Gossens, Michael Lindemann, Maarten De Vos
The results show that the proposed model is promising to achieve personalized longitudinal MS assessment; they also suggest that features related to gait and balance as well as upper extremity function, remotely collected from sensor-based assessments, may be useful digital markers for predicting MS over time.
1 code implementation • 22 Aug 2022 • Huy Phan, Cong Shi, Yi Xie, Tianfang Zhang, Zhuohang Li, Tianming Zhao, Jian Liu, Yan Wang, Yingying Chen, Bo Yuan
Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models.
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 • 29 Dec 2021 • Elisabeth R. M. Heremans, Huy Phan, Amir H. Ansari, Pascal Borzée, Bertien Buyse, Dries Testelmans, Maarten De Vos
This method consists of training a model with larger amounts of data from the source modality and few paired samples of source and target modality.
4 code implementations • 16 Nov 2021 • Thi Ngoc Tho Nguyen, Douglas L. Jones, Karn N. Watcharasupat, Huy Phan, Woon-Seng Gan
In this work, we introduce SALSA-Lite, a fast and effective feature for polyphonic SELD using microphone array inputs.
no code implementations • 3 Nov 2021 • Huy Phan, Kaare Mikkelsen
Modern deep learning holds a great potential to transform clinical practice on human sleep.
1 code implementation • NeurIPS 2021 • Yang Sui, Miao Yin, Yi Xie, Huy Phan, Saman Zonouz, Bo Yuan
Filter pruning has been widely used for neural network compression because of its enabled practical acceleration.
no code implementations • 18 Oct 2021 • Marco Comunità, Huy Phan, Joshua D. Reiss
Footsteps are among the most ubiquitous sound effects in multimedia applications.
no code implementations • 23 Aug 2021 • Huy Phan, Alfred Mertins, Mathias Baumert
Background: Despite the tremendous progress recently made towards automatic sleep staging in adults, it is currently unknown if the most advanced algorithms generalize to the pediatric population, which displays distinctive characteristics in overnight polysomnography (PSG).
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 • 9 Apr 2021 • Kaare B. Mikkelsen, Huy Phan, Mike L. Rank, Martin C. Hemmsen, Maarten De Vos, Preben Kidmose
Modern sleep monitoring development is shifting towards the use of unobtrusive sensors combined with algorithms for automatic sleep scoring.
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 • 7 Feb 2021 • Phairot Autthasan, Rattanaphon Chaisaen, Thapanun Sudhawiyangkul, Phurin Rangpong, Suktipol Kiatthaveephong, Nat Dilokthanakul, Gun Bhakdisongkhram, Huy Phan, Cuntai Guan, Theerawit Wilaiprasitporn
We integrate deep metric learning into a multi-task autoencoder to learn a compact and discriminative latent representation from EEG and perform classification simultaneously.
no code implementations • 26 Dec 2020 • Lam Pham, Huy Phan, Ross King, Alfred Mertins, Ian McLoughlin
This paper presents an inception-based deep neural network for detecting lung diseases using respiratory sound input.
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 SHHS
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.
1 code implementation • 8 Apr 2020 • Nannapas Banluesombatkul, Pichayoot Ouppaphan, Pitshaporn Leelaarporn, Payongkit Lakhan, Busarakum Chaitusaney, Nattapong Jaimchariyatam, Ekapol Chuangsuwanich, Wei Chen, Huy Phan, Nat Dilokthanakul, Theerawit Wilaiprasitporn
This is the first work that investigated a non-conventional pre-training method, MAML, resulting in a possibility for human-machine collaboration in sleep stage classification and easing the burden of the clinicians in labelling the sleep stages through only several epochs rather than an entire recording.
no code implementations • 4 Apr 2020 • Lam Pham, Huy Phan, Ramaswamy Palaniappan, Alfred Mertins, Ian McLoughlin
This paper presents and explores a robust deep learning framework for auscultation analysis.
no code implementations • 21 Jan 2020 • Lam Pham, Ian McLoughlin, Huy Phan, Minh Tran, Truc Nguyen, Ramaswamy Palaniappan
This paper presents a robust deep learning framework developed to detect respiratory diseases from recordings of respiratory sounds.
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.
no code implementations • 16 Dec 2019 • Huy Phan, Yi Xie, Siyu Liao, Jie Chen, Bo Yuan
In addition, CAG exhibits high transferability across different DNN classifier models in black-box attack scenario by introducing random dropout in the process of generating perturbations.
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.
2 code implementations • 28 Sep 2018 • Huy Phan, Fernando Andreotti, Navin Cooray, Oliver Y. Chén, Maarten De Vos
At the sequence processing level, a recurrent layer placed on top of the learned epoch-wise features for long-term modelling of sequential epochs.
1 code implementation • 16 May 2018 • Huy Phan, Fernando Andreotti, Navin Cooray, Oliver Y. Chén, Maarten De Vos
While the proposed framework is orthogonal to the widely adopted classification schemes, which take one or multiple epochs as contextual inputs and produce a single classification decision on the target epoch, we demonstrate its advantages in several ways.
Ranked #2 on
Sleep Stage Detection
on MASS SS2
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 • 10 Aug 2017 • Huy Phan, Martin Krawczyk-Becker, Timo Gerkmann, Alfred Mertins
Our proposed systems significantly outperform the challenge baseline, improving F-score from 72. 7% to 90. 0% and reducing detection error rate from 0. 53 to 0. 18 on average on the development data.
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.
1 code implementation • 11 Jul 2016 • Lars Hertel, Huy Phan, Alfred Mertins
We trained a deep all-convolutional neural network with masked global pooling to perform single-label classification for acoustic scene classification and multi-label classification for domestic audio tagging in the DCASE-2016 contest.
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.
no code implementations • 29 Apr 2016 • Huy Phan, Marco Maass, Lars Hertel, Radoslaw Mazur, Ian McLoughlin, Alfred Mertins
The entries of the descriptor are produced by evaluating a set of regressors on the input signal.
1 code implementation • 21 Apr 2016 • Huy Phan, Lars Hertel, Marco Maass, Alfred Mertins
We present in this paper a simple, yet efficient convolutional neural network (CNN) architecture for robust audio event recognition.
no code implementations • 18 Mar 2016 • Lars Hertel, Huy Phan, Alfred Mertins
Recognizing acoustic events is an intricate problem for a machine and an emerging field of research.