Search

Although many numerical methods can accurately solve time-domain electromagnetic (EM) simulation problems, such as finite-difference time-domain (FDTD), the computational demands are usually significant for complex scenarios. In this letter, we investigate the feasibility of applying deep learning technology to accurately solving EM forward simulations. Based on an end-to-end neural network framework, a convolutional neural network is used to extract features of scatters, and a long short-term memory neural network is used to predict EM distributions. To ensure the accuracy of the framework, especially when dealing with complicated phenomena, principal component analysis is employed to compress data sets before training. Numerical experiments show that the proposed scheme can predict EM field distributions efficiently and accurately for complex scenarios containing scatters of different materials, locations, geometrical shapes, and random numbers. The average relative mean square error is around 8. 05e−5 for scenarios with certain number of scatters and 2.25e−4 for random number of scatters respectively, which outperforms other neural network frameworks. Meanwhile, compared with FDTD, the time speedup is around 1528 times.

Replay speech poses a growing threat to speaker verification systems, thus the detection of replay speech becomes increasingly important. A critical factor differentiating replay speech and genuine speech is the representation of device information. Replay speech carries physical device information that originates from recording device, playback device, and environmental noise. In this work, a device-related linear transformation strategy is proposed to disentangle non-device information from replay speech. First, we conduct factor analysis by introducing a common vector for both replay utterance and the corresponding genuine speech utterance on parallel training data; then, we derive an expectation maximization formula to obtain the parameters of the device-related linear transformation; subsequently, three device feature extraction methods are developed based on the device-related linear transformation. The developed device features are evaluated on ASVspoof 2017 version 2.0 and ASVspoof 2021 physical access corpora. The experimental results demonstrate that our proposed linear transformation strategy is effective for replay spoofing detection, and the resultant device features outperform many typical features. Moreover, our spoofing detection systems display superior performance over several competitive state-of-the-art systems.

Behind the prevalence of multimedia technology, digital copyright disputes are becoming increasingly serious. The digital watermarking prevention technique against the copyright infringement needs to be improved urgently. Among the proposed technologies, zero-watermarking has been favored recently. In order to improve the robustness of the zero-watermarking, a novel robust audio zerowatermarking method based on sparse representation is proposed. The proposed scheme is mainly based on the K-singular value decomposition (K-SVD) algorithm to construct an optimal over complete dictionary from the background audio signal. After that, the orthogonal matching pursuit (OMP) algorithm is used to calculate the sparse coefficient of the segmented test audio and generate the corresponding sparse coefficient matrix. Then, the mean value of absolute sparse coefficients in the sparse matrix of segmented speech is calculated and selected, and then comparing the mean absolute coefficient of segmented speech with the average value of the selected coefficients to realize the embedding of zero-watermarking. Experimental results show that the proposed audio zero-watermarking algorithm based on sparse representation performs effectively in resisting various common attacks. Compared with the baseline works, the proposed method has better robustness.

An i-vector is a compact representation that captures both the speaker and session variabilities rendered in a spoken utterance. Over the past years, it has prevailed over other techniques and is now the de facto representation for text-independent speaker recognition. Standard i-vector extraction requires intense computation at run-time. Reducing the computation will allow effective use of i-vector in more applications. Such intense computation arises from the posterior covariance matrix, when estimating the i-vector. There have been studies on how to simplify the computation of posterior covariance matrix with modest success. In this paper, we propose a novel approach to i-vector extraction without the need to evaluate the full posterior covariance thereby speeding up the run-time extraction process. This is achieved by generalizing the i-vector estimation in two ways. First, we introduce the use of occupancy reweighting in conjunction with whitening over the Baum-Welch statistics as part of the preprocessing step. Second, we introduce the so-called subspace-orthogonalizing prior (SOP) to replace the standard Gaussian prior in i-vector formulation. Experiments conducted on the extended-core task of NIST SRE'10 show that the proposed rapid SOP approach achieves considerable speed-up over the standard i-vector with comparable equal error rates.

The identity vector (i-vector) approach has been the state-of-the-art for text-independent speaker recognition, both identification and verification in recent years. An i-vector is a low-dimensional vector in the socalled total variability space represented with a thin and tall rectangular matrix. This paper introduces a novel algorithm to improve the computational and memory requirements for the application. In our method, the series of symmetric matrices can be represented by diagonal expression, sharing the same dictionary, which to some extent is analogous to eigen decomposition, and we name this algorithm Eigen decomposition like factorization (EDLF). Similar algorithms are listed for comparison, in the same condition, our method shows no disadvantages in identification accuracy.