arXiv subjects

Jing Lu

Publications and source records attributed to Jing Lu.

At least 145 records · Page 8Linked to original sources

arXiv2021

DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement

The dual-path RNN (DPRNN) was proposed to more effectively model extremely long sequences for speech separation in the time domain. By splitting long sequences to smaller chunks and applying intra-chunk and inter-chunk RNNs, the DPRNN reached promising performance in speech separation with a limited model size. In this paper, we combine the DPRNN module with Convolution Recurrent Network (CRN) and design a model called Dual-Path Convolution Recurrent Network (DPCRN) for speech enhancement in the time-frequency domain. We replace the RNNs in the CRN with DPRNN modules, where the intra-chunk RNNs are used to model the spectrum pattern in a single frame and the inter-chunk RNNs are used to model the dependence between consecutive frames. With only 0.8M parameters, the submitted DPCRN model achieves an overall mean opinion score (MOS) of 3.57 in the wide band scenario track of the Interspeech 2021 Deep Noise Suppression (DNS) challenge. Evaluations on some other test sets also show the efficacy of our model.

cs.SD↗

arXiv2021

Few-photon optical diode in a chiral waveguide

We study the coherent transport of one or two photons in a 1D waveguide chirally coupled to a nonlinear resonator. Analytic solutions of the one-photon and two-photon scattering is derived. Although the resonator acts as a non-reciprocal phase shifter, light transmission is reciprocal at one-photon level. However, the forward and reverse transmitted probabilities for two photons incident from either the left side or the right side of the nonlinear resonator are nonreciprocal due to the energy redistribution of the two-photon bound state. Hence, the nonlinear resonator acts as an optical diode at two-photon level.

quant-ph↗

arXiv2021

[Ag(NH3)2]2SO4: A coordination strategy on the cationic-moiety to design nonlinear optical materials

Over decades, guided by the anionic group theory, the majority work has been focused on the anionic-moiety of a nonlinear optical material, however, the property guided structure modification and design on the cationic-moiety has long been neglected. Herein, we report for the first time a coordination strategy on the cationic-moiety, as demonstrated by the first exmple, [Ag(NH3)2]2SO4 vs Ag2SO4, the coordination of the plus one Ag+ cation by the neutral ligand forming the [Ag(NH3)2]+ cationic-moiety drives the formation of the noncentrosymmetric tetragonal P-421c structure which exhibits a remarkable property improvement, including a strong SHG intersity (1.4*KDP vs 0 @1064 nm), and a large birefringence (delta(n)cal.: 0.102 vs 0.012 @1064 nm). Furthermore, we discover that owing to the strong hydrogen bonds and spatial confinement of [SO4]2- anions, the cation [Ag(NH3)2]+ bends parallel to the crystallographic c axis with a bond angle of N-Ag-N = 174.35deg, generating a permenant dipole moment z = -0.12 D that is responsible for the large birefringence that enlarges the range of the phase matching SHG laser output. We believe what we discover is only a glimpse of the long been neglected crystal engineering on the cationic-moiety. Encourage by this work, exciting works on other ionic compound systems shall flood in.

cond-mat.mtrl-sci↗

arXiv2021

Semi-Blind Source Separation for Nonlinear Acoustic Echo Cancellation

The mismatch between the numerical and actual nonlinear models is a challenge to nonlinear acoustic echo cancellation (NAEC) when the nonlinear adaptive filter is utilized. To alleviate this problem, we combine a basis-generic expansion of the memoryless nonlinearity into semi-blind source separation (SBSS). By regarding all the basis functions of the far-end input signal as the known equivalent reference signals, an SBSS updating algorithm is derived following the constrained scaled natural gradient strategy. Unlike the commonly utilized adaptive algorithm, the proposed SBSS is based on the independence between the near-end signal and the reference signals, and is less sensitive to the mismatch of nonlinearity between the numerical and actual models. Experimental results show that the proposed method outperforms conventional methods in terms of echo return loss enhancement (ERLE) and near-end speech quality evaluated by perceptual evaluation of speech quality (PESQ) and short-time objective intelligibility (STOI).

eess.SP↗

arXiv2021

Coronary Plaque Analysis for CT Angiography Clinical Research

The analysis of plaque deposits in the coronary vasculature is an important topic in current clinical research. From a technical side mostly new algorithms for different sub tasks - e.g. centerline extraction or vessel/plaque segmentation - are proposed. However, to enable clinical research with the help of these algorithms, a software solution, which enables manual correction, comprehensive visual feedback and tissue analysis capabilities, is needed. Therefore, we want to present such an integrated software solution. It is able to perform robust automatic centerline extraction and inner and outer vessel wall segmentation, while providing easy to use manual correction tools. Also, it allows for annotation of lesions along the centerlines, which can be further analyzed regarding their tissue composition. Furthermore, it enables research in upcoming technologies and research directions: it does support dual energy CT scans with dedicated plaque analysis and the quantification of the fatty tissue surrounding the vasculature, also in automated set-ups.

cs.CV↗

arXiv2020

Nonexistence of k-bounded sobrification

In this paper, we will focus on k-bounded sober spaces and show the existence of a T_0 space X not admitting any k-bounded sobrification. This strengthens a result of Zhao, Lu and Wang, who proved that the canonical k-bounded sobrification does not exist. Our work provides a complete solution to a question of Zhao and Ho, and shows that unlike Sob and BSob,the category KBSob of all k-bounded sober spaces is not a reflective subcategory of the category Top_0 of all T_0 spaces. Furthermore, we introduce the notion of qk-bounded sober spaces and prove that the category KBSob is a full reflective subcategory of the category QKBSob of all qk-bounded sober spaces and continuous mappings preserving existing irreducible suprema.

math.GN↗

arXiv2020

Entanglement of Two Distinguishable Atoms in a Rectangular Waveguide: Linear Approximation with Single Excitation

We consider two two-level systems (TLSs) coupled to the vacuum of guided modes confined in a rectangular waveguide. Two TLSs are fixed at different points in the waveguide and initially share an excitation. For the energy separation of the TLSs far away from the cutoff frequencies of transverse modes, two coupled delay-differential equations are obtained for the probability amplitudes of the TLSs. The effects of the difference of TLSs' energy separations and the inter-TLS distance on the time evolution of the concurrence of the TLSs are examined.

quant-ph↗

arXiv2020

Target Speech Extraction Based on Blind Source Separation and X-vector-based Speaker Selection Trained with Data Augmentation

Extracting the desired speech from a mixture is a meaningful and challenging task. The end-to-end DNN-based methods, though attractive, face the problem of generalization. In this paper, we explore a sequential approach for target speech extraction by combining blind source separation (BSS) with the x-vector based speaker recognition (SR) module. Two promising BSS methods based on source independence assumption, independent low-rank matrix analysis (ILRMA) and multi-channel variational autoencoder (MVAE), are utilized and compared. ILRMA employs nonnegative matrix factorization (NMF) to capture spectral structures of source signals and MVAE utilizes the strong modeling power of deep neural networks (DNN). However, the investigation of MVAE has been limited to the training with very few speakers and the speech signals of test speakers are usually included. We extend the training of MVAE using clean speech signals of 500 speakers to evaluate its generalization to unseen speakers. To improve the correct extraction rate, two data augmentation strategies are implemented to train the SR module. The performance of the proposed cascaded approach is investigated with test data constructed with real room impulse responses under varied environments.

eess.AS↗

arXiv2020

Neural Passage Retrieval with Improved Negative Contrast

In this paper we explore the effects of negative sampling in dual encoder models used to retrieve passages for automatic question answering. We explore four negative sampling strategies that complement the straightforward random sampling of negatives, typically used to train dual encoder models. Out of the four strategies, three are based on retrieval and one on heuristics. Our retrieval-based strategies are based on the semantic similarity and the lexical overlap between questions and passages. We train the dual encoder models in two stages: pre-training with synthetic data and fine tuning with domain-specific data. We apply negative sampling to both stages. The approach is evaluated in two passage retrieval tasks. Even though it is not evident that there is one single sampling strategy that works best in all the tasks, it is clear that our strategies contribute to improving the contrast between the response and all the other passages. Furthermore, mixing the negatives from different strategies achieve performance on par with the best performing strategy in all tasks. Our results establish a new state-of-the-art level of performance on two of the open-domain question answering datasets that we evaluated.

cs.CL↗

arXiv2020

Valley pseudospin in monolayer MoSi2N4 and MoSi2As4

For a long time, two-dimensional (2D) hexagonal MoS2 was proposed as a promising material for valleytronic system. However, the limited size of growth and low carrier motilities in MoS2 restrict its further application. Very recently, a new kind of hexagonal 2D MXene, MoSi2N4, was successfully synthesized with large size, excellent ambient stability, and considerable hole mobility. In this paper, based on the first-principles calculations, we predict that the valley-contrast properties can be realized in monolayer MoSi2N4 and its derivative MoSi2As4. Beyond the traditional two-level valleys, the valleys in monolayer MoSi2As4 are multiple-folded, implying a new valley dimension. Such multiple-folded valleys can be described by a three-band low-power Hamiltonian. This study presents the theoretical advance and the potential applications of monolayer MoSi2N4 and MoSi2As4 in valleytronic devices, especially multiple information processing.

cond-mat.mtrl-sci↗

arXiv2020

Kalman Filtering Attention for User Behavior Modeling in CTR Prediction

Click-through rate (CTR) prediction is one of the fundamental tasks for e-commerce search engines. As search becomes more personalized, it is necessary to capture the user interest from rich behavior data. Existing user behavior modeling algorithms develop different attention mechanisms to emphasize query-relevant behaviors and suppress irrelevant ones. Despite being extensively studied, these attentions still suffer from two limitations. First, conventional attentions mostly limit the attention field only to a single user's behaviors, which is not suitable in e-commerce where users often hunt for new demands that are irrelevant to any historical behaviors. Second, these attentions are usually biased towards frequent behaviors, which is unreasonable since high frequency does not necessarily indicate great importance. To tackle the two limitations, we propose a novel attention mechanism, termed Kalman Filtering Attention (KFAtt), that considers the weighted pooling in attention as a maximum a posteriori (MAP) estimation. By incorporating a priori, KFAtt resorts to global statistics when few user behaviors are relevant. Moreover, a frequency capping mechanism is incorporated to correct the bias towards frequent behaviors. Offline experiments on both benchmark and a 10 billion scale real production dataset, together with an Online A/B test, show that KFAtt outperforms all compared state-of-the-arts. KFAtt has been deployed in the ranking system of a leading e commerce website, serving the main traffic of hundreds of millions of active users everyday.

cs.LG↗

arXiv2020

Entanglement of Two Jaynes-Cummings Atoms In Single Excitation Space

We study the entanglement dynamics of two atoms coupled to their own Jaynes-Cummings cavities in single-excitation space. Here we use the concurrence to measure the atomic entanglement. And the partial Bell states as initial states are considered. Our analysis suggests that there exist collapses and recovers in the entanglement dynamics. The physical mechanism behind the entanglement dynamics is the periodical information and energy exchange between atoms and light fields. For the initial Partial Bell states, only if the ratio of two atom-cavity coupling strengths is a rational number, the evolutionary periodicity of the atomic entanglement can be found. And whether there is time translation between two kinds of initial partial Bell state cases depends on the odd-even number of the coupling strength ratio.

quant-ph↗

arXiv2020

improving partition-block-based acoustic echo canceler in under-modeling scenarios

Recently, a partitioned-block-based frequency-domain Kalman filter (PFKF) has been proposed for acoustic echo cancellation. Compared with the normal frequency-domain Kalman filter, the PFKF utilizes the partitioned-block structure, resulting in both fast convergence and low time-latency. We present an analysis of the steady-state behavior of the PFKF and found that it suffers from a biased steady-state solution when the filter is of deficient length. Accordingly, we propose an effective modification that has the benefit of the guaranteed optimal steady-state behavior. Simulations are conducted to validate the improved performance of the proposed method.

eess.AS↗

arXiv2020

U-net Based Direct-path Dominance Test for Robust Direction-of-arrival Estimation

It has been noted that the identification of the time-frequency bins dominated by the contribution from the direct propagation of the target speaker can significantly improve the robustness of the direction-of-arrival estimation. However, the correct extraction of the direct-path sound is challenging especially in adverse environments. In this paper, a U-net based direct-path dominance test method is proposed. Exploiting the efficient segmentation capability of the U-net architecture, the direct-path information can be effectively retrieved from a dedicated multi-task neural network. Moreover, the training and inference of the neural network only need the input of a single microphone, circumventing the problem of array-structure dependence faced by common end-to-end deep learning based methods. Simulations demonstrate that significantly higher estimation accuracy can be achieved in high reverberant and low signal-to-noise ratio environments.

eess.AS↗

arXiv2020

Efficient Independent Vector Extraction of Dominant Target Speech

The complete decomposition performed by blind source separation is computationally demanding and superfluous when only the speech of one specific target speaker is desired. In this paper, we propose a computationally efficient blind speech extraction method based on a proper modification of the commonly utilized independent vector analysis algorithm, under the mild assumption that the average power of signal of interest outweighs interfering speech sources. Considering that the minimum distortion principle cannot be implemented since the full demixing matrix is not available, we also design a one-unit scaling operation to solve the scaling ambiguity. Simulations validate the efficacy of the proposed method in extracting the dominant speech.

cs.SD↗

arXiv2020

Category-Specific CNN for Visual-aware CTR Prediction at JD.com

As one of the largest B2C e-commerce platforms in China, JD com also powers a leading advertising system, serving millions of advertisers with fingertip connection to hundreds of millions of customers. In our system, as well as most e-commerce scenarios, ads are displayed with images.This makes visual-aware Click Through Rate (CTR) prediction of crucial importance to both business effectiveness and user experience. Existing algorithms usually extract visual features using off-the-shelf Convolutional Neural Networks (CNNs) and late fuse the visual and non-visual features for the finally predicted CTR. Despite being extensively studied, this field still face two key challenges. First, although encouraging progress has been made in offline studies, applying CNNs in real systems remains non-trivial, due to the strict requirements for efficient end-to-end training and low-latency online serving. Second, the off-the-shelf CNNs and late fusion architectures are suboptimal. Specifically, off-the-shelf CNNs were designed for classification thus never take categories as input features. While in e-commerce, categories are precisely labeled and contain abundant visual priors that will help the visual modeling. Unaware of the ad category, these CNNs may extract some unnecessary category-unrelated features, wasting CNN's limited expression ability. To overcome the two challenges, we propose Category-specific CNN (CSCNN) specially for CTR prediction. CSCNN early incorporates the category knowledge with a light-weighted attention-module on each convolutional layer. This enables CSCNN to extract expressive category-specific visual patterns that benefit the CTR prediction. Offline experiments on benchmark and a 10 billion scale real production dataset from JD, together with an Online A/B test show that CSCNN outperforms all compared state-of-the-art algorithms.

cs.LG↗

arXiv2020

Object-QA: Towards High Reliable Object Quality Assessment

In object recognition applications, object images usually appear with different quality levels. Practically, it is very important to indicate object image qualities for better application performance, e.g. filtering out low-quality object image frames to maintain robust video object recognition results and speed up inference. However, no previous works are explicitly proposed for addressing the problem. In this paper, we define the problem of object quality assessment for the first time and propose an effective approach named Object-QA to assess high-reliable quality scores for object images. Concretely, Object-QA first employs a well-designed relative quality assessing module that learns the intra-class-level quality scores by referring to the difference between object images and their estimated templates. Then an absolute quality assessing module is designed to generate the final quality scores by aligning the quality score distributions in inter-class. Besides, Object-QA can be implemented with only object-level annotations, and is also easily deployed to a variety of object recognition tasks. To our best knowledge this is the first work to put forward the definition of this problem and conduct quantitative evaluations. Validations on 5 different datasets show that Object-QA can not only assess high-reliable quality scores according with human cognition, but also improve application performance.

cs.CV↗

arXiv2020

Nonlinear Residual Echo Suppression Based on Multi-stream Conv-TasNet

Acoustic echo cannot be entirely removed by linear adaptive filters due to the nonlinear relationship between the echo and far-end signal. Usually a post processing module is required to further suppress the echo. In this paper, we propose a residual echo suppression method based on the modification of fully convolutional time-domain audio separation network (Conv-TasNet). Both the residual signal of the linear acoustic echo cancellation system, and the output of the adaptive filter are adopted to form multiple streams for the Conv-TasNet, resulting in more effective echo suppression while keeping a lower latency of the whole system. Simulation results validate the efficacy of the proposed method in both single-talk and double-talk situations.

eess.AS↗