In this article, we first establish the theory of optimal scores for speaker recognition. Our analysis shows that the minimum Bayes risk (MBR) decisions for both the speaker identification and speaker verification tasks can be based on a normalized likelihood (NL). When the underlying generative model is a linear Gaussian, the NL score is mathematically equivalent to the PLDA likelihood ratio, and the empirical scores based on cosine distance and Euclidean distance can be seen as approximations of this linear Gaussian NL score under some conditions. We discuss a number of properties of the NL score and perform a simple simulation experiment to demonstrate the properties of the NL score.
Domain mismatch often occurs in real applications and causes serious performance reduction on speaker verification systems. The common wisdom is to collect cross-domain data and train a multi-domain PLDA model, with the hope to learn a domain-independent speaker subspace. In this paper, we firstly present an empirical study to show that simply adding cross-domain data does not help performance in conditions with enrollment-test mismatch. Careful analysis shows that this striking result is caused by the incoherent statistics between the enrollment and test conditions. Based on this analysis, we present a decoupled scoring approach that can maximally squeeze the value of cross-domain labels and obtain optimal verification scores when the enrollment and test are mismatched. When the statistics are coherent, the new formulation falls back to the conventional PLDA. Experimental results on cross-channel test show that the proposed approach is highly effective and is a principle solution to domain mismatch.
Various information factors are blended in speech signals, which forms the primary difficulty for most speech information processing tasks. An intuitive idea is to factorize speech signal into individual information factors (e.g., phonetic content and speaker trait), though it turns out to be highly challenging. This paper presents a speech factorization approach based on a novel factorial discriminative normalization flow model (factorial DNF). Experiments conducted on a two-factor case that involves phonetic content and speaker trait demonstrates that the proposed factorial DNF has powerful capability to factorize speech signals and outperforms several comparative models in terms of information representation and manipulation.
Archetypal analysis is an unsupervised learning method that uses a convex polytope to summarize multivariate data. For fixed $k$, the method finds a convex polytope with $k$ vertices, called archetype points, such that the polytope is contained in the convex hull of the data and the mean squared distance between the data and the polytope is minimal. In this paper, we prove a consistency result that shows if the data is independently sampled from a probability measure with bounded support, then the archetype points converge to a solution of the continuum version of the problem, of which we identify and establish several properties. We also obtain the convergence rate of the optimal objective values under appropriate assumptions on the distribution. If the data is independently sampled from a distribution with unbounded support, we also prove a consistency result for a modified method that penalizes the dispersion of the archetype points. Our analysis is supported by detailed computational experiments of the archetype points for data sampled from the uniform distribution in a disk, the normal distribution, an annular distribution, and a Gaussian mixture model.
In this paper, we present a method to efficiently generate large, free, and guaranteed convex space among arbitrarily cluttered obstacles. Our method operates directly on point clouds, avoids expensive calculations, and processes thousands of points within a few milliseconds, which extremely suits embedded platforms. The base stone of our method is sphere flipping, a one-one invertible nonlinear transformation, which maps a set of unordered points to a nonlinear space. With these wrapped points, we obtain a collision-free star convex polytope. Then, utilizing the star convexity, we efficiently modify the polytope to convex and guarantee its free of obstacles. Extensive quantitative evaluations show that our method significantly outperforms state-of-the-art works in efficiency. We also present practical applications with our method in 3D, including large-scale deformable topological mapping and quadrotor optimal trajectory planning, to validate its capability and efficiency. The source code of our method will be released for the reference of the community.
In this study, we propose a novel RGB-T tracking framework by jointly modeling both appearance and motion cues. First, to obtain a robust appearance model, we develop a novel late fusion method to infer the fusion weight maps of both RGB and thermal (T) modalities. The fusion weights are determined by using offline-trained global and local multimodal fusion networks, and then adopted to linearly combine the response maps of RGB and T modalities. Second, when the appearance cue is unreliable, we comprehensively take motion cues, i.e., target and camera motions, into account to make the tracker robust. We further propose a tracker switcher to switch the appearance and motion trackers flexibly. Numerous results on three recent RGB-T tracking datasets show that the proposed tracker performs significantly better than other state-of-the-art algorithms.
In recent years, the multiple-stage strategy has become a popular trend for visual tracking. This strategy first utilizes a base tracker to coarsely locate the target and then exploits a refinement module to obtain more accurate results. However, existing refinement modules suffer from the limited transferability and precision. In this work, we propose a novel, flexible and accurate refinement module called Alpha-Refine, which exploits a precise pixel-wise correlation layer together with a spatial-aware non-local layer to fuse features and can predict three complementary outputs: bounding box, corners and mask. To wisely choose the most adequate output, we also design a light-weight branch selector module. We apply the proposed Alpha-Refine module to five famous and state-of-the-art base trackers: DiMP, ATOM, SiamRPN++, RTMDNet and ECO. The comprehensive experiments on TrackingNet, LaSOT and VOT2018 benchmarks demonstrate that our approach significantly improves the tracking performance in comparison with other existing refinement methods. The source codes will be available at https://github.com/MasterBin-IIAU/AlphaRefine.
The geodesic active contour model (GAC) is a commonly used segmentation model for medical image segmentation. The level set method (LSM) is the most popular approach for solving the model, via implicitly representing the contour by a level set function. However, the LSM suffers from high computation burden and numerical instability, requiring additional regularization terms or re-initialization techniques. In this paper, we use characteristic functions to implicitly approximate the contours, propose a new representation to the GAC and derive an efficient algorithm termed as the iterative convolution-thresholding method (ICTM). Compared to the LSM, the ICTM is simpler and much more efficient and stable. In addition, the ICTM enjoys most desired features (e.g., topological changes) of the level set-based methods. Extensive experiments, on 2D synthetic, 2D ultrasound, 3D CT, and 3D MR images for nodule, organ and lesion segmentation, demonstrate that the ICTM not only obtains comparable or even better segmentation results (compared to the LSM) but also achieves dozens or hundreds of times acceleration.
This paper introduces the fifth oriental language recognition (OLR) challenge AP20-OLR, which intends to improve the performance of language recognition systems, along with APSIPA Annual Summit and Conference (APSIPA ASC). The data profile, three tasks, the corresponding baselines, and the evaluation principles are introduced in this paper. The AP20-OLR challenge includes more languages, dialects and real-life data provided by Speechocean and the NSFC M2ASR project, and all the data is free for participants. The challenge this year still focuses on practical and challenging problems, with three tasks: (1) cross-channel LID, (2) dialect identification and (3) noisy LID. Based on Kaldi and Pytorch, recipes for i-vector and x-vector systems are also conducted as baselines for the three tasks. These recipes will be online-published, and available for participants to configure LID systems. The baseline results on the three tasks demonstrate that those tasks in this challenge are worth paying more efforts to achieve better performance.