Sound Event Detection Via Dilated Convolutional Recurrent Neural Networks

Li, Yanxiong; Liu, Mingle; Drossos, Konstantinos; Virtanen, Tuomas

doi:10.1109/icassp40776.2020.9054433

Cited by 45 publications

(31 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It would also be interesting to implement the system on hardware to test its performance under real-life scenarios. Finally, more sophisticated signal-processing deep learning models [26], [27], albeit being more computationally expensive for real-time applications, are also worth being explored as well.…”

Section: Resultsmentioning

confidence: 99%

Intelliquench: An Adaptive Machine Learning System for Detection of Superconducting Magnet Quenches

Hoang

Boffo

Tran

et al. 2021

IEEE Trans. Appl. Supercond.

View full text Add to dashboard Cite

In superconducting magnets, the irreversible transition of a portion of the conductor to resistive state is called a "quench." Having large stored energy, magnets can be damaged by quenches due to localized heating, high voltage, or large force transients. Unfortunately, current quench protection systems can only detect a quench after it happens, and mitigating risks in Low Temperature Superconducting (LTS) accelerator magnets often requires fast response (down to ms). Additionally, protection of High Temperature Superconducting (HTS) magnets is still suffering from prohibitively slow quench detection. In this study, we lay the groundwork for a quench prediction system using an auto-encoder fully-connected deep neural network. After dynamically trained with data features extracted from acoustic sensors around the magnet, the system detects anomalous events seconds before the quench in most of our data. While the exact nature of the events is under investigation, we show that the system can "forecast" a quench before it happens under magnet training conditions through a randomized experiment. This opens up the way of integrated data processing, potentially leading to faster and better diagnostics and detection of magnet quenches.

show abstract

Section: Resultsmentioning

confidence: 99%

Intelliquench: An Adaptive Machine Learning System for Detection of Superconducting Magnet Quenches

Hoang

Boffo

Tran

et al. 2021

IEEE Trans. Appl. Supercond.

View full text Add to dashboard Cite

show abstract

“…The kernel dilation could be used in any combination (for example, dilation in time dimension or feature dimension only) or all combinations of its dimensions. Li et al provided a method to combine dilated convolution with RNN in audio classification task [ 36 ], which clearly focused on the exploration and learning of long-term patterns. Drossos et al proposed an improved Convolutional Recursive Neural Network (CRNN) structure [ 31 ] which used DWS and dilated convolution with dilation in the time dimension only, i.e., time-dilated convolution.…”

Section: Related Workmentioning

confidence: 99%

Underwater Acoustic Target Recognition Based on Depthwise Separable Convolution Neural Networks

Wang

Liu

2021

Sensors

View full text Add to dashboard Cite

Facing the complex marine environment, it is extremely challenging to conduct underwater acoustic target feature extraction and recognition using ship-radiated noise. In this paper, firstly, taking the one-dimensional time-domain raw signal of the ship as the input of the model, a new deep neural network model for underwater target recognition is proposed. Depthwise separable convolution and time-dilated convolution are used for passive underwater acoustic target recognition for the first time. The proposed model realizes automatic feature extraction from the raw data of ship radiated noise and temporal attention in the process of underwater target recognition. Secondly, the measured data are used to evaluate the model, and cluster analysis and visualization analysis are performed based on the features extracted from the model. The results show that the features extracted from the model have good characteristics of intra-class aggregation and inter-class separation. Furthermore, the cross-folding model is used to verify that there is no overfitting in the model, which improves the generalization ability of the model. Finally, the model is compared with traditional underwater acoustic target recognition, and its accuracy is significantly improved by 6.8%.

show abstract

“…1D CNN was chosen as a shallow benchmark learner as it enables frame-level investigation, and its use had been explored for audio recognition and Natural Language Processing (NLP). 1D CNN has been used with raw waveform and usually combined with a Recurrent Neural Network (RNN) in audio applications [ 75 ]. The convolution layer’s kernel size in our benchmark 1D CNN is set to 3, and 24 filters were used with a ReLU activation.…”

Section: Performance Comparisonmentioning

confidence: 99%

Robust Computationally-Efficient Wireless Emitter Classification Using Autoencoders and Convolutional Neural Networks

Almazrouei

Gianini

Almoosa

et al. 2021

Sensors

View full text Add to dashboard Cite

This paper proposes a novel Deep Learning (DL)-based approach for classifying the radio-access technology (RAT) of wireless emitters. The approach improves computational efficiency and accuracy under harsh channel conditions with respect to existing approaches. Intelligent spectrum monitoring is a crucial enabler for emerging wireless access environments that supports sharing of (and dynamic access to) spectral resources between multiple RATs and user classes. Emitter classification enables monitoring the varying patterns of spectral occupancy across RATs, which is instrumental in optimizing spectral utilization and interference management and supporting efficient enforcement of access regulations. Existing emitter classification approaches successfully leverage convolutional neural networks (CNNs) to recognize RAT visual features in spectrograms and other time-frequency representations; however, the corresponding classification accuracy degrades severely under harsh propagation conditions, and the computational cost of CNNs may limit their adoption in resource-constrained network edge scenarios. In this work, we propose a novel emitter classification solution consisting of a Denoising Autoencoder (DAE), which feeds a CNN classifier with lower dimensionality, denoised representations of channel-corrupted spectrograms. We demonstrate—using a standard-compliant simulation of various RATs including LTE and four latest Wi-Fi standards—that in harsh channel conditions including non-line-of-sight, large scale fading, and mobility-induced Doppler shifts, our proposed solution outperforms a wide range of standalone CNNs and other machine learning models while requiring significantly less computational resources. The maximum achieved accuracy of the emitter classifier is 100%, and the average accuracy is 91% across all the propagation conditions.

show abstract

Sound Event Detection Via Dilated Convolutional Recurrent Neural Networks

Cited by 45 publications

References 20 publications

Intelliquench: An Adaptive Machine Learning System for Detection of Superconducting Magnet Quenches

Intelliquench: An Adaptive Machine Learning System for Detection of Superconducting Magnet Quenches

Underwater Acoustic Target Recognition Based on Depthwise Separable Convolution Neural Networks

Robust Computationally-Efficient Wireless Emitter Classification Using Autoencoders and Convolutional Neural Networks

Contact Info

Product

Resources

About