arXiv subjects

Weibin Zhang

Publications and source records attributed to Weibin Zhang.

26 records · Page 2Linked to original sources

arXiv2022

The CORAL++ Algorithm for Unsupervised Domain Adaptation of Speaker Recogntion

State-of-the-art speaker recognition systems are trained with a large amount of human-labeled training data set. Such a training set is usually composed of various data sources to enhance the modeling capability of models. However, in practical deployment, unseen condition is almost inevitable. Domain mismatch is a common problem in real-life applications due to the statistical difference between the training and testing data sets. To alleviate the degradation caused by domain mismatch, we propose a new feature-based unsupervised domain adaptation algorithm. The algorithm we propose is a further optimization based on the well-known CORrelation ALignment (CORAL), so we call it CORAL++. On the NIST 2019 Speaker Recognition Evaluation (SRE19), we use SRE18 CTS set as the development set to verify the effectiveness of CORAL++. With the typical x-vector/PLDA setup, the CORAL++ outperforms the CORAL by 9.40% relatively on EER.

eess.AS↗

arXiv2021

Estimation of Covariance Matrix of Interference for Secure Spatial Modulation against a Malicious Full-duplex Attacker

In a secure spatial modulation with a malicious full-duplex attacker, how to obtain the interference space or channel state information (CSI) is very important for Bob to cancel or reduce the interference from Mallory. In this paper, different from existing work with a perfect CSI, the covariance matrix of malicious interference (CMMI) from Mallory is estimated and is used to construct the null-space of interference (NSI). Finally, the receive beamformer at Bob is designed to remove the malicious interference using the NSI. To improve the estimation accuracy, a rank detector relying on Akaike information criterion (AIC) is derived. To achieve a high-precision CMMI estimation, two methods are proposed as follows: principal component analysis-eigenvalue decomposition (PCA-EVD), and joint diagonalization (JD). The proposed PCA-EVD is a rank deduction method whereas the JD method is a joint optimization method with improved performance in low signal to interference plus noise ratio (SINR) region at the expense of increased complexities. Simulation results show that the proposed PCA-EVD performs much better than the existing method like sample estimated covariance matrix (SCM) and EVD in terms of normalized mean square error (NMSE) and secrecy rate (SR). Additionally, the proposed JD method has an excellent NMSE performance better than PCA-EVD in the low SINR region (SINR < 0dB) while in the high SINR region PCA-EVD performs better than JD.

cs.IT↗

arXiv2020

Multi-head Monotonic Chunkwise Attention For Online Speech Recognition

The attention mechanism of the Listen, Attend and Spell (LAS) model requires the whole input sequence to calculate the attention context and thus is not suitable for online speech recognition. To deal with this problem, we propose multi-head monotonic chunk-wise attention (MTH-MoChA), an improved version of MoChA. MTH-MoChA splits the input sequence into small chunks and computes multi-head attentions over the chunks. We also explore useful training strategies such as LSTM pooling, minimum world error rate training and SpecAugment to further improve the performance of MTH-MoChA. Experiments on AISHELL-1 data show that the proposed model, along with the training strategies, improve the character error rate (CER) of MoChA from 8.96% to 7.68% on test set. On another 18000 hours in-car speech data set, MTH-MoChA obtains 7.28% CER, which is significantly better than a state-of-the-art hybrid system.

cs.CL↗

arXiv2020

Vehicle Tracking in Wireless Sensor Networks via Deep Reinforcement Learning

Vehicle tracking has become one of the key applications of wireless sensor networks (WSNs) in the fields of rescue, surveillance, traffic monitoring, etc. However, the increased tracking accuracy requires more energy consumption. In this letter, a decentralized vehicle tracking strategy is conceived for improving both tracking accuracy and energy saving, which is based on adjusting the intersection area between the fixed sensing area and the dynamic activation area. Then, two deep reinforcement learning (DRL) aided solutions are proposed relying on the dynamic selection of the activation area radius. Finally, simulation results show the superiority of our DRL aided design.

eess.SY↗

arXiv2020

Receive Antenna Selection for Secure Pre-coding Aided Spatial Modulation

In this paper, we make an investigation of receive antenna selection (RAS) strategies in the secure pre-coding aided spatial modulation (PSM) system with the aid of artificial noise. Due to a lack of the closed-form expression for secrecy rate (SR) in secure PSM systems, it is hard to optimize the RAS. To address this issue, the cut-off rate is used as an approximation of the SR. Further, two low-complexity RAS schemes for maximizing SR, called Max-SR-L and Max-SR-H, are derived in the low and high signal-to-noise ratio (SNR) regions, respectively. Due to the fact that the former works well in the low SNR region but becomes worse in the medium and high SNR regions while the latter also has the similar problem, a novel RAS strategy Max-SR-A is proposed to cover all SNR regions. Simulation results show that the proposed Max-SR-H and Max-SR-L schemes approach the optimal SR performances of the exhaustive search (ES) in the high and low SNR regions, respectively. In particular, the SR performance of the proposed Max-SR-A is close to that of the optimal ES and better than that of the random method in almost all SNR regions.

cs.IT↗

arXiv2019

Fluctuations and Correlations in a Model of Extreme Introverts and Extroverts

Unlike typical phase transitions of first and second order, a system displaying the Thouless effect exhibits characteristics of both at the critical point (jumps in the order parameter and anomalously large fluctuations). An $extreme$ Thousless effect was observed in a recently introduced model of social networks consisting of `introverts and extroverts' ($XIE$). We study the fluctuations and correlations of this system using both Monte Carlo simulations and analytic methods based on a self-consistent mean field theory. Due to the symmetries in the model, we derive identities between all independent two point correlations and fluctuations in three quantities (degrees of individuals and the total number of links between the two subgroups) in the stationary state. As simulations confirm these identities, we study only the fluctuations in detail. Though qualitatively similar to those in the 2D Ising model, there are several unusual aspects, due to the extreme Thouless effect. All these anomalous fluctuations can be quantitatively understood with our theory, despite the mean-field aspects in the approximations. In our theory, we frequently encounter the `finite Poisson distribution' (i.e., $x^{n}/n!$ for $n\in \left[ 0,N\right] $ and zero otherwise). Since its properties appear to be quite obscure, we include an Appendix on the details and the related `finite exponential series' $\sum_{0}^{N}x^{n}/n!$. Some simulation studies of joint degree distributions, which provide a different perspective on correlations, have also been carried out.

physics.soc-ph↗

arXiv2019

Essence Knowledge Distillation for Speech Recognition

It is well known that a speech recognition system that combines multiple acoustic models trained on the same data significantly outperforms a single-model system. Unfortunately, real time speech recognition using a whole ensemble of models is too computationally expensive. In this paper, we propose to distill the knowledge of essence in an ensemble of models (i.e. the teacher model) to a single model (i.e. the student model) that needs much less computation to deploy. Previously, all the soften outputs of the teacher model are used to optimize the student model. We argue that not all the outputs of the ensemble are necessary to be distilled. Some of the outputs may even contain noisy information that is useless or even harmful to the training of the student model. In addition, we propose to train the student model with a multitask learning approach by utilizing both the soften outputs of the teacher model and the correct hard labels. The proposed method achieves some surprising results on the Switchboard data set. When the student model is trained together with the correct labels and the essence knowledge from the teacher model, it not only significantly outperforms another single model with the same architecture that is trained only with the correct labels, but also consistently outperforms the teacher model that is used to generate the soft labels.

cs.CL↗

arXiv2018

Exact results for the extreme Thouless effect in a model of network dynamics

If a system undergoing phase transitions exhibits some characteristics of both first and second order, it is said to be of 'mixed order' or to display the Thouless effect. Such a transition is present in a simple model of a dynamic social network, in which $N_{I/E}$ extreme introverts/extroverts always cut/add random links. In particular, simulations showed that $\left\langle f\right\rangle $, the average fraction of cross-links between the two groups (which serves as an 'order parameter' here), jumps dramatically when $Δ\equiv N_{I}-N_{E}$ crosses the 'critical point' $Δ_{c}=0$, as in typical first order transitions. Yet, at criticality, there is no phase co-existence, but the fluctuations of $f$ are much larger than in typical second order transitions. Indeed, it was conjectured that, in the thermodynamic limit, both the jump and the fluctuations become maximal, so that the system is said to display an 'extreme Thouless effect.' While earlier theories are partially successful, we provide a mean-field like approach that accounts for all known simulation data and validates the conjecture. Moreover, for the critical system $N_{I}=N_{E}=L$, an analytic expression for the mesa-like stationary distribution, $P\left( f\right) $, shows that it is essentially flat in a range $\left[ f_{0},1-f_{0}\right] $, with $f_0 \ll 1$. Numerical evaluations of $f_{0}$ provides excellent agreement with simulation data for $L\lesssim 2000$. For large $L$, we find $f_{0}\rightarrow \sqrt{\left( \ln L^2 \right) /L}$ , though this behavior begins to set in only for $L>10^{100}$. For accessible values of $L$, we provide a transcendental equation for an approximate $f_{0}$ which is better than $\sim$1% down to $L=100$. We conjecture how this approach might be used to attack other systems displaying an extreme Thouless effect.

physics.soc-ph↗