Searcharxiv⌕ Search

arXiv subjects

Quan Wang

Publications and source records attributed to Quan Wang.

At least 181 records · Page 10Linked to original sources

Attention-Based Models for Text-Dependent Speaker Verification

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire length of an input sequence. In this paper, we analyze the usage of attention mechanisms to the problem of sequence summarization in our end-to-end text-dependent speaker recognition system. We explore different topologies and their variants of the attention layer, and compare different pooling methods on the attention weights. Ultimately, we show that attention-based models can improves the Equal Error Rate (EER) of our speaker verification system by relatively 14% compared to our non-attention LSTM baseline model.

eess.AS↗

Links: A High-Dimensional Online Clustering Method

We present a novel algorithm, called Links, designed to perform online clustering on unit vectors in a high-dimensional Euclidean space. The algorithm is appropriate when it is necessary to cluster data efficiently as it streams in, and is to be contrasted with traditional batch clustering algorithms that have access to all data at once. For example, Links has been successfully applied to embedding vectors generated from face images or voice recordings for the purpose of recognizing people, thereby providing real-time identification during video or audio capture.

stat.ML↗

Leveraging Text and Knowledge Bases for Triple Scoring: An Ensemble Approach - The BOKCHOY Triple Scorer at WSDM Cup 2017

We present our winning solution for the WSDM Cup 2017 triple scoring task. We devise an ensemble of four base scorers, so as to leverage the power of both text and knowledge bases for that task. Then we further refine the outputs of the ensemble by trigger word detection, achieving even better predictive accuracy. The code is available at https://github.com/wsdm-cup-2017/bokchoy.

cs.IR↗

Wavenet based low rate speech coding

Traditional parametric coding of speech facilitates low rate but provides poor reconstruction quality because of the inadequacy of the model used. We describe how a WaveNet generative speech model can be used to generate high quality speech from the bit stream of a standard parametric coder operating at 2.4 kb/s. We compare this parametric coder with a waveform coder based on the same generative model and show that approximating the signal waveform incurs a large rate penalty. Our experiments confirm the high performance of the WaveNet based coder and show that the speech produced by the system is able to additionally perform implicit bandwidth extension and does not significantly impair recognition of the original speaker for the human listener, even when that speaker has not been used during the training of the generative model.

eess.AS↗

Knowledge Graph Embedding with Iterative Guidance from Soft Rules

Embedding knowledge graphs (KGs) into continuous vector spaces is a focus of current research. Combining such an embedding model with logic rules has recently attracted increasing attention. Most previous attempts made a one-time injection of logic rules, ignoring the interactive nature between embedding learning and logical inference. And they focused only on hard rules, which always hold with no exception and usually require extensive manual effort to create or validate. In this paper, we propose Rule-Guided Embedding (RUGE), a novel paradigm of KG embedding with iterative guidance from soft rules. RUGE enables an embedding model to learn simultaneously from 1) labeled triples that have been directly observed in a given KG, 2) unlabeled triples whose labels are going to be predicted iteratively, and 3) soft rules with various confidence levels extracted automatically from the KG. In the learning process, RUGE iteratively queries rules to obtain soft labels for unlabeled triples, and integrates such newly labeled triples to update the embedding model. Through this iterative procedure, knowledge embodied in logic rules may be better transferred into the learned embeddings. We evaluate RUGE in link prediction on Freebase and YAGO. Experimental results show that: 1) with rule knowledge injected iteratively, RUGE achieves significant and consistent improvements over state-of-the-art baselines; and 2) despite their uncertainties, automatically extracted soft rules are highly beneficial to KG embedding, even those with moderate confidence levels. The code and data used for this paper can be obtained from https://github.com/iieir-km/RUGE.

cs.AI↗

Distributed Simulation Platform for Autonomous Driving

Autonomous vehicle safety and reliability are the paramount requirements when developing autonomous vehicles. These requirements are guaranteed by massive functional and performance tests. Conducting these tests on real vehicles is extremely expensive and time consuming, and thus it is imperative to develop a simulation platform to perform these tasks. For simulation, we can utilize the Robot Operating System (ROS) for data playback to test newly developed algorithms. However, due to the massive amount of simulation data, performing simulation on single machines is not practical. Hence, a high-performance distributed simulation platform is a critical piece in autonomous driving development. In this paper we present our experiences of building a production distributed autonomous driving simulation platform. This platform is built upon Spark distributed framework, for distributed computing management, and ROS, for data playback simulations.

cs.DC↗

Implementing a Cloud Platform for Autonomous Driving

Autonomous driving clouds provide essential services to support autonomous vehicles. Today these services include but not limited to distributed simulation tests for new algorithm deployment, offline deep learning model training, and High-Definition (HD) map generation. These services require infrastructure support including distributed computing, distributed storage, as well as heterogeneous computing. In this paper, we present the details of how we implement a unified autonomous driving cloud infrastructure, and how we support these services on top of this infrastructure.

cs.DC↗

Dynamic bifurcation and instability of Dean problem

The main objective of this paper is to address the instability and dynamical bifurcation of the Dean problem. A nonlinear theory is obtained for the Dean problem, leading in particular to rigorous justifications of the linear theory used by physicists, and the vortex structure. The main technical tools are the dynamic bifurcation theory [15] developed recently by Ma and Wang.

math.AP↗

Kernel Principal Component Analysis and its Applications in Face Recognition and Active Shape Models

Principal component analysis (PCA) is a popular tool for linear dimensionality reduction and feature extraction. Kernel PCA is the nonlinear form of PCA, which better exploits the complicated spatial structure of high-dimensional features. In this paper, we first review the basic ideas of PCA and kernel PCA. Then we focus on the reconstruction of pre-images for kernel PCA. We also give an introduction on how PCA is used in active shape models (ASMs), and discuss how kernel PCA can be applied to improve traditional ASMs. Then we show some experimental results to compare the performance of kernel PCA and standard PCA for classification problems. We also implement the kernel PCA-based ASMs, and use it to construct human face models.

cs.CV↗

MuSR Investigation and Suppression of TC by overdoped Li in Diluted Ferromagnetic Semiconductor Li1+y(Zn1-xMnx)P

We use muon spin relaxation (muSR) to investigate the magnetic properties of a bulk form diluted ferromagnetic semiconductor (DFS) Li1.15(Zn0.9Mn0.1)P with T_C ~ 22 K. MuSR results confirm the gradual development of ferromagnetic ordering below T_C with a nearly 100% magnetic ordered volume. Despite its low carrier density, the relation between static internal field and Curie temperature observed for Li(Zn,Mn)P is consistent with the trend found in (Ga,Mn)As and other bulk DFSs, indicating these systems share a common mechanism for the ferromagnetic exchange interaction. Li1+y(Zn1-xMnx)P has the advantage of decoupled carrier and spin doping, where Mn2+ substitution for Zn2+ introduces spins and Li+ off-stoichiometry provides carriers. This advantage enables us to investigate the influence of overdoped Li on the ferromagnetic ordered state. Overdoping Li suppresses both T_C and saturation moments for a certain amount of spins, which indicates that more carriers are detrimental to the ferromagnetic exchange interaction, and that a delicate balance between charge and spin densities is required to achieve highest T_C.

cond-mat.mtrl-sci↗

Li1.1(Zn1-xCrx)As: Cr doped I-II-V Diluted Magnetic Semiconductors in Bulk Form

We report the synthesis and characterization of bulk form diluted magnetic semiconductors I-II-V Li1.1(Zn1-xCrx)As (x = 0.03, 0.05, 0.10, 0.15)with a cubic crystal structure identical to that of III-V GaAs and II-VI zinc-blende ZnSe. With p-type carriers created by excess Li, 10% Cr substitution for Zn results in a ferromagnetic ordering below TC ~ 218 K. Li(Zn,Cr)As represents another magnetic semiconducting system with the advantage of decoupling carriers and spins, where carriers are created by adding extra Li and spins are introduced by Cr substitution for Zn.

cond-mat.str-el↗

31P NMR Investigation of the Superconductor LiFeP (Tc = 5 K)

We investigate the static and dynamic spin susceptibility of the 111 type Fe-based superconductor LiFeP with Tc ~ 5 K through the measurement of Knight shift 31K and the spin-lattice relaxation rate 1/T1 at 31P site by nuclear magnetic resonance. The constant 31K, small magnitudes of 1/T1T, along with the resistivity rho ~ T^2 all point to the weak spin correlations in LiFeP. 1/T1T display small enhancement toward Tc, indicating that the superconductivity is intimately correlated with the antiferromagnetic spin fluctuations.

cond-mat.supr-con↗

Ba(Zn1-2xMnxCox)2As2: A Bulk Form Diluted Magnetic Semiconductor with n-type Carriers

We report the synthesis and characterization of bulk form diluted magnetic semiconductors Ba(Zn1-2xMnxCox)2As2 (0 <= x <= 0.15) with a crystal structure identical to that of 122-type Fe-based superconductors. Mn and Co co-doping into the parent compound BaZn2As2 results in a ferromagnetic ordering below TC ~ 80 K. Hall effect measurements indicate that the carrier are n-type with the density of ~10^17/cm3. The common crystal structure and excellent lattice matching between the p-type ferromagnetic (Ba1-yKy)(Zn1-xMnx)2As2, the n-type ferromagnetic Ba(Zn1-2xMnxCox)2As2, the antiferrmagnetic BaMn2As2 and the superconducting Ba(Fe1-xCox)2As2 systems make it possible to make various junctions between these systems through the As layer.

cond-mat.str-el↗

(Sr3La2O5)(Zn1-xMnx)2As2: A Bulk Form Diluted Magnetic Semiconductor isostructural to the "32522" Fe-based Superconductors

A new diluted magnetic semiconductor system, (Sr3La2O5)(Zn1-xMnx)2As2, has been synthesized and characterized. 10% Mn substitution for Zn in bulk form (Sr3La2O5)Zn2As2 results in a ferromagnetic ordering below Curie temperature, TC ~ 40 K. (Sr3La2O5)(Zn1-xMnx)2As2 has a layered crystal structure identical to that of 32522-type Fe based superconductors, and represents the fifth DMS family that has a direct counterpart among the FeAs high temperature superconductor families.

cond-mat.str-el↗

A predicable condition for boundary layer separation of 2-D incompressible fluid flows

In this paper, the solutions of Navier-Stokes equations with Dirichlet boundary conditions governing 2-D incompressible fluid flows are considered. A condition for boundary layer separation, which is determined by initial values and external forces, is obtained. More importantly, the condition can predict directly when and where boundary layer separation will occur. The main technical tool is geometric theory of incompressible flows developed by T. Ma and S.Wang.

physics.flu-dyn↗

The synthesis and characterization of 1111-type diluted magnetic semiconductors (La1-xSrx)(Zn1-xTMx)AsO (TM = Mn, Fe, Co)

The doping effect of Sr and transition metals Mn, Fe, Co into the direct-gap semiconductor LaZnAsO has been investigated. Our results indicate that the single phase ZrCuSiAs-type tetragonal crystal structure is preserved in (La1-xSrx)(Zn1-xTMx)AsO (TM = Mn, Fe, Co) with the doping level up to x = 0.1. While the system remains semiconducting, doping with Sr and Mn results in ferromagnetic order with TC ~ 30K, and doping with Sr and Fe results in a spin glass like state below ~6K with a saturation moment of ~0.02 muB/Fe, an order of magnitude smaller than the ~0.4 muB/Mn of Sr and Mn doped samples. The same type of magnetic state is observed neither for (Zn,Fe) substitution without carrier doping, nor for Sr and Co doped specimens.

cond-mat.str-el↗

(La1-xBax)(Zn1-xMnx)AsO: A Two Dimensional "1111" Diluted Magnetic Semiconductor in Bulk Form

We report the synthesis and characterization of a bulk diluted magnetic semiconductor (La1-xBax)(Zn1-xMnx)AsO (0 <= x <= 0.2) with a layered crystal structure identical to that of the "1111" FeAs superconductors. No ferromagnetic order occurs for (Zn,Mn) substitution in the parent compound LaZnAsO without charge doping. Together with carrier doping via (La,Ba) sub- stitution, a small amount of Mn substituting for Zn results in ferromagnetic order with TC up to ~40 K, although the system remains semiconducting. Muon spin relaxation measurements confirm the development of ferromagnetic order in the entire volume, with the relationship between the internal field and TC consistent with the trend found in (Ga,Mn)As, the "111" Li(Zn,Mn)As, and the "122" (Ba,K)(Zn,Mn)2As2 systems.

cond-mat.str-el↗

Feature Learning by Multidimensional Scaling and its Applications in Object Recognition

We present the MDS feature learning framework, in which multidimensional scaling (MDS) is applied on high-level pairwise image distances to learn fixed-length vector representations of images. The aspects of the images that are captured by the learned features, which we call MDS features, completely depend on what kind of image distance measurement is employed. With properly selected semantics-sensitive image distances, the MDS features provide rich semantic information about the images that is not captured by other feature extraction techniques. In our work, we introduce the iterated Levenberg-Marquardt algorithm for solving MDS, and study the MDS feature learning with IMage Euclidean Distance (IMED) and Spatial Pyramid Matching (SPM) distance. We present experiments on both synthetic data and real images --- the publicly accessible UIUC car image dataset. The MDS features based on SPM distance achieve exceptional performance for the car recognition task.

cs.CV↗