Deep learning algorithm are increasingly used for speech enhancement (SE). In supervised methods, global and local information is required for accurate spectral mapping. A key restriction is often poor capture of key contextual information. To leverage long-term for target speakers and compensate distortions of cleaned speech, this paper adopts a sequence-to-sequence (S2S) mapping structure and proposes a novel monaural speech enhancement system, consisting of a Feature Extraction Block (FEB), a Compensation Enhancement Block (ComEB) and a Mask Block (MB). In the FEB a U-net block is used to extract abstract features using complex-valued spectra with one path to suppress the background noise in the magnitude domain using masking methods and the MB takes magnitude features from the FEBand compensates the lost complex-domain features produced from ComEB to restore the final cleaned speech. Experiments are conducted on the Librispeech dataset and results show that the proposed model obtains better performance than recent models in terms of ESTOI and PESQ scores.
相關內容
Recently studies on time-domain audio separation networks (TasNets) have made a great stride in speech separation. One of the most representative TasNets is a network with a dual-path segmentation approach. However, the original model called DPRNN used a fixed feature dimension and unchanged segment size throughout all layers of the network. In this paper, we propose a multi-scale feature fusion transformer network (MSFFT-Net) based on the conventional dual-path structure for single-channel speech separation. Unlike the conventional dual-path structure where only one processing path exists, adopting several iterative blocks with alternative intra-chunk and inter-chunk operations to capture local and global context information, the proposed MSFFT-Net has multiple parallel processing paths where the feature information can be exchanged between multiple parallel processing paths. Experiments show that our proposed networks based on multi-scale feature fusion structure have achieved better results than the original dual-path model on the benchmark dataset-WSJ0-2mix, where the SI-SNRi score of MSFFT-3P is 20.7dB (1.47% improvement), and MSFFT-2P is 21.0dB (3.45% improvement), which achieves SOTA on WSJ0-2mix without any data augmentation method.
Recognizing human emotions from complex, multivariate, and non-stationary electroencephalography (EEG) time series is essential in affective brain-computer interface. However, because continuous labeling of ever-changing emotional states is not feasible in practice, existing methods can only assign a fixed label to all EEG timepoints in a continuous emotion-evoking trial, which overlooks the highly dynamic emotional states and highly non-stationary EEG signals. To solve the problems of high reliance on fixed labels and ignorance of time-changing information, in this paper we propose a time-aware sampling network (TAS-Net) using deep reinforcement learning (DRL) for unsupervised emotion recognition, which is able to detect key emotion fragments and disregard irrelevant and misleading parts. Extensive experiments are conducted on three public datasets (SEED, DEAP, and MAHNOB-HCI) for emotion recognition using leave-one-subject-out cross-validation, and the results demonstrate the superiority of the proposed method against previous unsupervised emotion recognition methods.
Building segmentation in high-resolution InSAR images is a challenging task that can be useful for large-scale surveillance. Although complex-valued deep learning networks perform better than their real-valued counterparts for complex-valued SAR data, phase information is not retained throughout the network, which causes a loss of information. This paper proposes a Fully Complex-valued, Fully Convolutional Multi-feature Fusion Network(FC2MFN) for building semantic segmentation on InSAR images using a novel, fully complex-valued learning scheme. The network learns multi-scale features, performs multi-feature fusion, and has a complex-valued output. For the particularity of complex-valued InSAR data, a new complex-valued pooling layer is proposed that compares complex numbers considering their magnitude and phase. This helps the network retain the phase information even through the pooling layer. Experimental results on the simulated InSAR dataset show that FC2MFN achieves better results compared to other state-of-the-art methods in terms of segmentation performance and model complexity.
Object detection and classification using aerial images is a challenging task as the information regarding targets are not abundant. Synthetic Aperture Radar(SAR) images can be used for Automatic Target Recognition(ATR) systems as it can operate in all-weather conditions and in low light settings. But, SAR images contain salt and pepper noise(speckle noise) that cause hindrance for the deep learning models to extract meaningful features. Using just aerial view Electro-optical(EO) images for ATR systems may also not result in high accuracy as these images are of low resolution and also do not provide ample information in extreme weather conditions. Therefore, information from multiple sensors can be used to enhance the performance of Automatic Target Recognition(ATR) systems. In this paper, we explore a methodology to use both EO and SAR sensor information to effectively improve the performance of the ATR systems by handling the shortcomings of each of the sensors. A novel Multi-Modal Domain Fusion(MDF) network is proposed to learn the domain invariant features from multi-modal data and use it to accurately classify the aerial view objects. The proposed MDF network achieves top-10 performance in the Track-1 with an accuracy of 25.3 % and top-5 performance in Track-2 with an accuracy of 34.26 % in the test phase on the PBVS MAVOC Challenge dataset [18].
Video enhancement is a challenging problem, more than that of stills, mainly due to high computational cost, larger data volumes and the difficulty of achieving consistency in the spatio-temporal domain. In practice, these challenges are often coupled with the lack of example pairs, which inhibits the application of supervised learning strategies. To address these challenges, we propose an efficient adversarial video enhancement framework that learns directly from unpaired video examples. In particular, our framework introduces new recurrent cells that consist of interleaved local and global modules for implicit integration of spatial and temporal information. The proposed design allows our recurrent cells to efficiently propagate spatio-temporal information across frames and reduces the need for high complexity networks. Our setting enables learning from unpaired videos in a cyclic adversarial manner, where the proposed recurrent units are employed in all architectures. Efficient training is accomplished by introducing one single discriminator that learns the joint distribution of source and target domain simultaneously. The enhancement results demonstrate clear superiority of the proposed video enhancer over the state-of-the-art methods, in all terms of visual quality, quantitative metrics, and inference speed. Notably, our video enhancer is capable of enhancing over 35 frames per second of FullHD video (1080x1920).
Anomaly detection is important in many real-life applications. Recently, self-supervised learning has greatly helped deep anomaly detection by recognizing several geometric transformations. However these methods lack finer features, usually highly depend on the anomaly type, and do not perform well on fine-grained problems. To address these issues, we first introduce in this work three novel and efficient discriminative and generative tasks which have complementary strength: (i) a piece-wise jigsaw puzzle task focuses on structure cues; (ii) a tint rotation recognition is used within each piece, taking into account the colorimetry information; (iii) and a partial re-colorization task considers the image texture. In order to make the re-colorization task more object-oriented than background-oriented, we propose to include the contextual color information of the image border via an attention mechanism. We then present a new out-of-distribution detection function and highlight its better stability compared to existing methods. Along with it, we also experiment different score fusion functions. Finally, we evaluate our method on an extensive protocol composed of various anomaly types, from object anomalies, style anomalies with fine-grained classification to local anomalies with face anti-spoofing datasets. Our model significantly outperforms state-of-the-art with up to 36% relative error improvement on object anomalies and 40% on face anti-spoofing problems.
With the rapid development of facial forgery techniques, forgery detection has attracted more and more attention due to security concerns. Existing approaches attempt to use frequency information to mine subtle artifacts under high-quality forged faces. However, the exploitation of frequency information is coarse-grained, and more importantly, their vanilla learning process struggles to extract fine-grained forgery traces. To address this issue, we propose a progressive enhancement learning framework to exploit both the RGB and fine-grained frequency clues. Specifically, we perform a fine-grained decomposition of RGB images to completely decouple the real and fake traces in the frequency space. Subsequently, we propose a progressive enhancement learning framework based on a two-branch network, combined with self-enhancement and mutual-enhancement modules. The self-enhancement module captures the traces in different input spaces based on spatial noise enhancement and channel attention. The Mutual-enhancement module concurrently enhances RGB and frequency features by communicating in the shared spatial dimension. The progressive enhancement process facilitates the learning of discriminative features with fine-grained face forgery clues. Extensive experiments on several datasets show that our method outperforms the state-of-the-art face forgery detection methods.
Recently, graph neural networks (GNNs) have been widely used for document classification. However, most existing methods are based on static word co-occurrence graphs without sentence-level information, which poses three challenges:(1) word ambiguity, (2) word synonymity, and (3) dynamic contextual dependency. To address these challenges, we propose a novel GNN-based sparse structure learning model for inductive document classification. Specifically, a document-level graph is initially generated by a disjoint union of sentence-level word co-occurrence graphs. Our model collects a set of trainable edges connecting disjoint words between sentences and employs structure learning to sparsely select edges with dynamic contextual dependencies. Graphs with sparse structures can jointly exploit local and global contextual information in documents through GNNs. For inductive learning, the refined document graph is further fed into a general readout function for graph-level classification and optimization in an end-to-end manner. Extensive experiments on several real-world datasets demonstrate that the proposed model outperforms most state-of-the-art results, and reveal the necessity to learn sparse structures for each document.
Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data. Recent work on their expressive power has focused on isomorphism tasks and countable feature spaces. We extend this theoretical framework to include continuous features - which occur regularly in real-world input domains and within the hidden layers of GNNs - and we demonstrate the requirement for multiple aggregation functions in this context. Accordingly, we propose Principal Neighbourhood Aggregation (PNA), a novel architecture combining multiple aggregators with degree-scalers (which generalize the sum aggregator). Finally, we compare the capacity of different models to capture and exploit the graph structure via a novel benchmark containing multiple tasks taken from classical graph theory, alongside existing benchmarks from real-world domains, all of which demonstrate the strength of our model. With this work, we hope to steer some of the GNN research towards new aggregation methods which we believe are essential in the search for powerful and robust models.
In this paper, we propose a novel multi-task learning architecture, which incorporates recent advances in attention mechanisms. Our approach, the Multi-Task Attention Network (MTAN), consists of a single shared network containing a global feature pool, together with task-specific soft-attention modules, which are trainable in an end-to-end manner. These attention modules allow for learning of task-specific features from the global pool, whilst simultaneously allowing for features to be shared across different tasks. The architecture can be built upon any feed-forward neural network, is simple to implement, and is parameter efficient. Experiments on the CityScapes dataset show that our method outperforms several baselines in both single-task and multi-task learning, and is also more robust to the various weighting schemes in the multi-task loss function. We further explore the effectiveness of our method through experiments over a range of task complexities, and show how our method scales well with task complexity compared to baselines.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191