Related papers: Diversifying and Expanding Frequency-Adaptive Conv…
Domestic activities classification (DAC) from audio recordings aims at classifying audio recordings into pre-defined categories of domestic activities, which is an effective way for estimation of daily activities performed in home…
Hyperspectral imagery is rich in spatial and spectral information. Using 3D-CNN can simultaneously acquire features of spatial and spectral dimensions to facilitate classification of features, but hyperspectral image information spectral…
Convolutional neural networks (CNNs) have shown remarkable performance in various computer vision tasks in recent years. However, the increasing model size has raised challenges in adopting them in real-time applications as well as mobile…
Neural networks based on convolutional operations have achieved remarkable results in the field of deep learning, but there are two inherent flaws in standard convolutional operations. On the one hand, the convolution operation is confined…
Convolution is an essential operation in signal and image processing and consumes most of the computing power in convolutional neural networks. Photonic convolution has the promise of addressing computational bottlenecks and outperforming…
Multi-source data classification is a critical yet challenging task for remote sensing image interpretation. Existing methods lack adaptability to diverse land cover types when modeling frequency domain features. To this end, we propose a…
Deep neural network solutions have emerged as a new and powerful paradigm for speech enhancement (SE). The capabilities to capture long context and extract multi-scale patterns are crucial to design effective SE networks. Such capabilities,…
Deep convolutional neural networks have been proven successful in multiple benchmark challenges in recent years. However, the performance improvements are heavily reliant on increasingly complex network architecture and a high number of…
Music source separation involves a large input field to model a long-term dependence of an audio signal. Previous convolutional neural network (CNN)-based approaches address the large input field modeling using sequentially down- and…
In this paper, we propose a stacked convolutional and recurrent neural network (CRNN) with a 3D convolutional neural network (CNN) in the first layer for the multichannel sound event detection (SED) task. The 3D CNN enables the network to…
This paper proposes a Sub-band Convolutional Neural Network for spoken term classification. Convolutional neural networks (CNNs) have proven to be very effective in acoustic applications such as spoken term classification, keyword spotting,…
We propose a dynamic filtering strategy with large sampling field for ConvNets (LS-DFN), where the position-specific kernels learn from not only the identical position but also multiple sampled neighbor regions. During sampling, residual…
We propose a network for semantic mapping called the Dense Dilated Convolutions Merging Network (DDCM-Net) to provide a deep learning approach that can recognize multi-scale and complex shaped objects with similar color and textures, such…
Sound events often occur in unstructured environments where they exhibit wide variations in their frequency content and temporal structure. Convolutional neural networks (CNN) are able to extract higher level features that are invariant to…
Deep neural networks have demonstrated highly competitive performance in super-resolution (SR) for natural images by learning mappings from low-resolution (LR) to high-resolution (HR) images. However, hyperspectral super-resolution remains…
Deep learning-based speech enhancement (SE) models have recently outperformed traditional techniques, yet their deployment on resource-constrained devices remains challenging due to high computational and memory demands. This paper…
Task 4 of the DCASE2018 challenge demonstrated that substantially more research is needed for a real-world application of sound event detection. Analyzing the challenge results it can be seen that most successful models are biased towards…
Time delay neural networks (TDNNs) are an effective acoustic model for large vocabulary speech recognition. The strength of the model can be attributed to its ability to effectively model long temporal contexts. However, current TDNN models…
In order to handle modern convolutional neural networks (CNNs) efficiently, a hardware architecture of CNN inference accelerator is proposed to handle depthwise convolutions and regular convolutions, which are both essential building blocks…
Kernel-based approaches for sequence classification have been successfully applied to a variety of domains, including the text categorization, image classification, speech analysis, biological sequence analysis, time series and music…