Changhong Liu

Hui Yan, Zhenchun Lei, Changhong Liu et al.

With the development of deep learning, many different network architectures have been explored in speaker verification. However, most network architectures rely on a single deep learning architecture, and hybrid networks combining different architectures have been little studied in ASV tasks. In this paper, we propose the GMM-ResNext model for speaker verification. Conventional GMM does not consider the score distribution of each frame feature over all Gaussian components and ignores the relationship between neighboring speech frames. So, we extract the log Gaussian probability features based on the raw acoustic features and use ResNext-based network as the backbone to extract the speaker embedding. GMM-ResNext combines Generative and Discriminative Models to improve the generalization ability of deep learning models and allows one to more easily specify meaningful priors on model parameters. A two-path GMM-ResNext model based on two gender-related GMMs has also been proposed. The Experimental results show that the proposed GMM-ResNext achieves relative improvements of 48.1\% and 11.3\% in EER compared with ResNet34 and ECAPA-TDNN on VoxCeleb1-O test set.

Mingliang Li, Lin Yuanbo Wu, Changhong Liu et al.

The rapid advancement of deepfake generation techniques has intensified the need for robust and generalizable detection methods. Existing approaches based on reconstruction learning typically leverage deep convolutional networks to extract differential features. However, these methods show poor generalization across object categories (e.g., from faces to cars) and generation domains (e.g., from GANs to Stable Diffusion), due to intrinsic limitations of deep CNNs. First, models trained on a specific category tend to overfit to semantic feature distributions, making them less transferable to other categories, especially as network depth increases. Second, Global Average Pooling (GAP) compresses critical local forgery cues into a single vector, thus discarding discriminative patterns vital for real-fake classification. To address these issues, we propose a novel Local Focus Mechanism (LFM) that explicitly attends to discriminative local features for differentiating fake from real images. LFM integrates a Salience Network (SNet) with a task-specific Top-K Pooling (TKP) module to select the K most informative local patterns. To mitigate potential overfitting introduced by Top-K pooling, we introduce two regularization techniques: Rank-Based Linear Dropout (RBLD) and Random-K Sampling (RKS), which enhance the model's robustness. LFM achieves a 3.7 improvement in accuracy and a 2.8 increase in average precision over the state-of-the-art Neighboring Pixel Relationships (NPR) method, while maintaining exceptional efficiency at 1789 FPS on a single NVIDIA A6000 GPU. Our approach sets a new benchmark for cross-domain deepfake detection. The source code are available in https://github.com/lmlpy/LFM.git

Changhong Liu, Jingjing Wang, Qiaosheng Zhang et al.

The white book released by the International Telecommunications Union (ITU) calls for extremely high-security and low-latency communication over fading channels. Under the low-latency requirement, the corresponding fading model is quasi-static fading while high-security can be achieved via covert communication. In response to the call of ITU, we study the finite blocklength performance of optimal codes for covert communication over quasi-static multi-antenna fading channels, under the covertness metric of Kullback-Leibler (KL) divergence. In particular, we study all four cases regarding the availability of channel state information (CSI) for legitimate transmitter and receiver, and assume that the warden knows perfect CSI for the channel from the legitimate transmitter to itself. Specifically, we show that, when the blocklength is $n$, the first-order covert rate satisfies the square root law, scaling as $Θ(n^{-\frac{1}{2}})$ with the coefficient determined by the traces of the channel matrices of the legitimate users and the warden, and the second-order rate vanishes. In contrast to the non-covert result of Yang et al. (TIT, 2014), we show that CSI availability at the legitimate users does not affect the finite blocklength performance for covert communication. Furthermore, we reveal the significant spatial diversity gain provided by multiple-antenna systems for covert communication. For the covertness analysis, we extend the quasi-$η$-neighborhood framework to fading channels and address challenges arising from the random channel matrices. For the reliability analysis, due to the vanishing power imposed by the covertness constraint, we refine the non-covert analysis by Yang et al. (TIT, 2014), by carefully controlling higher-order terms and exploiting the properties of covert outage probability.