In this paper we introduce a first attempt on understanding how a non-autoregressive factorised multi-speaker speech synthesis architecture exploits the information present in different speaker embedding sets. We analyse if jointly learning the representations, and initialising them from pretrained models determine any quality improvements for target speaker identities. In a separate analysis, we investigate how the different sets of embeddings impact the network's core speech abstraction (i.e. zero conditioned) in terms of speaker identity and representation learning. We show that, regardless of the used set of embeddings and learning strategy, the network can handle various speaker identities equally well, with barely noticeable variations in speech output quality, and that speaker leakage within the core structure of the synthesis system is inevitable in the standard training procedures adopted thus far.
相關內容
A common phenomenon in spatial regression models is spatial confounding. This phenomenon occurs when spatially indexed covariates modeling the mean of the response are correlated with a spatial effect included in the model. spatial+ Dupont et al. (2022) is a popular approach to reducing spatial confounding. spatial+ is a two-stage frequentist approach that explicitly models the spatial structure in the confounded covariate, removes it, and uses the corresponding residuals in the second stage. In a frequentist setting, there is no uncertainty propagation from the first stage estimation determining the residuals since only point estimates are used. Inference can also be cumbersome in a frequentist setting, and some of the gaps in the original approach can easily be remedied in a Bayesian framework. First, a Bayesian joint model can easily achieve uncertainty propagation from the first to the second stage of the model. In a Bayesian framework, we also have the tools to infer the model's parameters directly. Notably, another advantage of using a Bayesian framework we thoroughly explore is the ability to use prior information to impose restrictions on the spatial effects rather than applying them directly to their posterior. We build a joint prior for the smoothness of all spatial effects that simultaneously shrinks towards a high smoothness of the response and imposes that the spatial effect in the response is a smoother of the confounded covariates' spatial effect. This prevents the response from operating at a smaller scale than the covariate and can help to avoid situations where there is insufficient variation in the residuals resulting from the first stage model. We evaluate the performance of the Bayesian spatial+ via both simulated and real datasets.
This paper introduces a novel approach for human-to-robot motion retargeting, enabling robots to mimic human motion with precision while preserving the semantics of the motion. For that, we propose a deep learning method for direct translation from human to robot motion. Our method does not require annotated paired human-to-robot motion data, which reduces the effort when adopting new robots. To this end, we first propose a cross-domain similarity metric to compare the poses from different domains (i.e., human and robot). Then, our method achieves the construction of a shared latent space via contrastive learning and decodes latent representations to robot motion control commands. The learned latent space exhibits expressiveness as it captures the motions precisely and allows direct motion control in the latent space. We showcase how to generate in-between motion through simple linear interpolation in the latent space between two projected human poses. Additionally, we conducted a comprehensive evaluation of robot control using diverse modality inputs, such as texts, RGB videos, and key-poses, which enhances the ease of robot control to users of all backgrounds. Finally, we compare our model with existing works and quantitatively and qualitatively demonstrate the effectiveness of our approach, enhancing natural human-robot communication and fostering trust in integrating robots into daily life.
In this research work, we propose a high-order time adapted scheme for pricing a coupled system of fixed-free boundary constant elasticity of variance (CEV) model on both equidistant and locally refined space-grid. The performance of our method is substantially enhanced to improve irregularities in the model which are both inherent and induced. Furthermore, the system of coupled PDEs is strongly nonlinear and involves several time-dependent coefficients that include the first-order derivative of the early exercise boundary. These coefficients are approximated from a fourth-order analytical approximation which is derived using a regularized square-root function. The semi-discrete equation for the option value and delta sensitivity is obtained from a non-uniform fourth-order compact finite difference scheme. Fifth-order 5(4) Dormand-Prince time integration method is used to solve the coupled system of discrete equations. Enhancing the performance of our proposed method with local mesh refinement and adaptive strategies enables us to obtain highly accurate solution with very coarse space grids, hence reducing computational runtime substantially. We further verify the performance of our methodology as compared with some of the well-known and better-performing existing methods.
In this paper, we propose a Riemannian Acceleration with Preconditioning (RAP) for symmetric eigenvalue problems, which is one of the most important geodesically convex optimization problem on Riemannian manifold, and obtain the acceleration. Firstly, the preconditioning for symmetric eigenvalue problems from the Riemannian manifold viewpoint is discussed. In order to obtain the local geodesic convexity, we develop the leading angle to measure the quality of the preconditioner for symmetric eigenvalue problems. A new Riemannian acceleration, called Locally Optimal Riemannian Accelerated Gradient (LORAG) method, is proposed to overcome the local geodesic convexity for symmetric eigenvalue problems. With similar techniques for RAGD and analysis of local convex optimization in Euclidean space, we analyze the convergence of LORAG. Incorporating the local geodesic convexity of symmetric eigenvalue problems under preconditioning with the LORAG, we propose the Riemannian Acceleration with Preconditioning (RAP) and prove its acceleration. Additionally, when the Schwarz preconditioner, especially the overlapping or non-overlapping domain decomposition method, is applied for elliptic eigenvalue problems, we also obtain the rate of convergence as $1-C\kappa^{-1/2}$, where $C$ is a constant independent of the mesh sizes and the eigenvalue gap, $\kappa=\kappa_{\nu}\lambda_{2}/(\lambda_{2}-\lambda_{1})$, $\kappa_{\nu}$ is the parameter from the stable decomposition, $\lambda_{1}$ and $\lambda_{2}$ are the smallest two eigenvalues of the elliptic operator. Numerical results show the power of Riemannian acceleration and preconditioning.
This paper explores the generalization characteristics of iterative learning algorithms with bounded updates for non-convex loss functions, employing information-theoretic techniques. Our key contribution is a novel bound for the generalization error of these algorithms with bounded updates, extending beyond the scope of previous works that only focused on Stochastic Gradient Descent (SGD). Our approach introduces two main novelties: 1) we reformulate the mutual information as the uncertainty of updates, providing a new perspective, and 2) instead of using the chaining rule of mutual information, we employ a variance decomposition technique to decompose information across iterations, allowing for a simpler surrogate process. We analyze our generalization bound under various settings and demonstrate improved bounds when the model dimension increases at the same rate as the number of training data samples. To bridge the gap between theory and practice, we also examine the previously observed scaling behavior in large language models. Ultimately, our work takes a further step for developing practical generalization theories.
This paper introduces non-linear dimension reduction in factor-augmented vector autoregressions to analyze the effects of different economic shocks. I argue that controlling for non-linearities between a large-dimensional dataset and the latent factors is particularly useful during turbulent times of the business cycle. In simulations, I show that non-linear dimension reduction techniques yield good forecasting performance, especially when data is highly volatile. In an empirical application, I identify a monetary policy as well as an uncertainty shock excluding and including observations of the COVID-19 pandemic. Those two applications suggest that the non-linear FAVAR approaches are capable of dealing with the large outliers caused by the COVID-19 pandemic and yield reliable results in both scenarios.
A new hybridizable discontinuous Galerkin method, named the CHDG method, is proposed for solving time-harmonic scalar wave propagation problems. This method relies on a standard discontinuous Galerkin scheme with upwind numerical fluxes and high-order polynomial bases. Auxiliary unknowns corresponding to characteristic variables are defined at the interface between the elements, and the physical fields are eliminated to obtain a reduced system. The reduced system can be written as a fixed-point problem that can be solved with stationary iterative schemes. Numerical results with 2D benchmarks are presented to study the performance of the approach. Compared to the standard HDG approach, the properties of the reduced system are improved with CHDG, which is more suited for iterative solution procedures. The condition number of the reduced system is smaller with CHDG than with the standard HDG method. Iterative solution procedures with CGNR or GMRES required smaller numbers of iterations with CHDG.
In this paper we establish limit theorems for power variations of stochastic processes controlled by fractional Brownian motions with Hurst parameter $H\leq 1/2$. We show that the power variations of such processes can be decomposed into the mix of several weighted random sums plus some remainder terms, and the convergences of power variations are dominated by different combinations of those weighted sums depending on whether $H<1/4$, $H=1/4$, or $H>1/4$. We show that when $H\geq 1/4$ the centered power variation converges stably at the rate $n^{-1/2}$, and when $H<1/4$ it converges in probability at the rate $n^{-2H}$. We determine the limit of the mixed weighted sum based on a rough path approach developed in \cite{LT20}.
We present a topological audio fingerprinting approach for robustly identifying duplicate audio tracks. Our method applies persistent homology on local spectral decompositions of audio signals, using filtered cubical complexes computed from mel-spectrograms. By encoding the audio content in terms of local Betti curves, our topological audio fingerprints enable accurate detection of time-aligned audio matchings. Experimental results demonstrate the accuracy of our algorithm in the detection of tracks with the same audio content, even when subjected to various obfuscations. Our approach outperforms existing methods in scenarios involving topological distortions, such as time stretching and pitch shifting.
In this paper, two novel classes of implicit exponential Runge-Kutta (ERK) methods are studied for solving highly oscillatory systems. Firstly, we analyze the symplectic conditions for two kinds of exponential integrators and obtain the symplectic method. In order to effectively solve highly oscillatory problems, we try to design the highly accurate implicit ERK integrators. By comparing the Taylor series expansion of numerical solution with exact solution, it can be verified that the order conditions of two new kinds of exponential methods are identical to classical Runge-Kutta (RK) methods, which implies that using the coefficients of RK methods, some highly accurate numerical methods are directly formulated. Furthermore, we also investigate the linear stability properties for these exponential methods. Finally, numerical results not only display the long time energy preservation of the symplectic method, but also present the accuracy and efficiency of these formulated methods in comparison with standard ERK methods.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191