Singing technique conversion (STC) refers to the task of converting from one voice technique to another while leaving the original singer identity, melody, and linguistic components intact. Previous STC studies, as well as singing voice conversion research in general, have utilized convolutional autoencoders (CAEs) for conversion, but how the bottleneck width of the CAE affects the synthesis quality has not been thoroughly evaluated. To this end, we constructed a GAN-based multi-domain STC system which took advantage of the WORLD vocoder representation and the CAE architecture. We varied the bottleneck width of the CAE, and evaluated the conversion results subjectively. The model was trained on a Mandarin dataset which features four singers and four singing techniques: the chest voice, the falsetto, the raspy voice, and the whistle voice. The results show that a wider bottleneck corresponds to better articulation clarity but does not necessarily lead to higher likeness to the target technique. Among the four techniques, we also found that the whistle voice is the easiest target for conversion, while the other three techniques as a source produce more convincing conversion results than the whistle.
相關內容
This paper rigorously shows how over-parameterization changes the convergence behaviors of gradient descent (GD) for the matrix sensing problem, where the goal is to recover an unknown low-rank ground-truth matrix from near-isotropic linear measurements. First, we consider the symmetric setting with the symmetric parameterization where $M^* \in \mathbb{R}^{n \times n}$ is a positive semi-definite unknown matrix of rank $r \ll n$, and one uses a symmetric parameterization $XX^\top$ to learn $M^*$. Here $X \in \mathbb{R}^{n \times k}$ with $k > r$ is the factor matrix. We give a novel $\Omega (1/T^2)$ lower bound of randomly initialized GD for the over-parameterized case ($k >r$) where $T$ is the number of iterations. This is in stark contrast to the exact-parameterization scenario ($k=r$) where the convergence rate is $\exp (-\Omega (T))$. Next, we study asymmetric setting where $M^* \in \mathbb{R}^{n_1 \times n_2}$ is the unknown matrix of rank $r \ll \min\{n_1,n_2\}$, and one uses an asymmetric parameterization $FG^\top$ to learn $M^*$ where $F \in \mathbb{R}^{n_1 \times k}$ and $G \in \mathbb{R}^{n_2 \times k}$. Building on prior work, we give a global exact convergence result of randomly initialized GD for the exact-parameterization case ($k=r$) with an $\exp (-\Omega(T))$ rate. Furthermore, we give the first global exact convergence result for the over-parameterization case ($k>r$) with an $\exp(-\Omega(\alpha^2 T))$ rate where $\alpha$ is the initialization scale. This linear convergence result in the over-parameterization case is especially significant because one can apply the asymmetric parameterization to the symmetric setting to speed up from $\Omega (1/T^2)$ to linear convergence. On the other hand, we propose a novel method that only modifies one step of GD and obtains a convergence rate independent of $\alpha$, recovering the rate in the exact-parameterization case.
Existing score-distilling text-to-3D generation techniques, despite their considerable promise, often encounter the view inconsistency problem. One of the most notable issues is the Janus problem, where the most canonical view of an object (\textit{e.g}., face or head) appears in other views. In this work, we explore existing frameworks for score-distilling text-to-3D generation and identify the main causes of the view inconsistency problem -- the embedded bias of 2D diffusion models. Based on these findings, we propose two approaches to debias the score-distillation frameworks for view-consistent text-to-3D generation. Our first approach, called score debiasing, involves cutting off the score estimated by 2D diffusion models and gradually increasing the truncation value throughout the optimization process. Our second approach, called prompt debiasing, identifies conflicting words between user prompts and view prompts using a language model, and adjusts the discrepancy between view prompts and the viewing direction of an object. Our experimental results show that our methods improve the realism of the generated 3D objects by significantly reducing artifacts and achieve a good trade-off between faithfulness to the 2D diffusion models and 3D consistency with little overhead. Our project page is available at~\url{//susunghong.github.io/Debiased-Score-Distillation-Sampling/}.
Deep Neural Networks and Reinforcement Learning methods have empirically shown great promise in tackling challenging combinatorial problems. In those methods a deep neural network is used as a solution generator which is then trained by gradient-based methods (e.g., policy gradient) to successively obtain better solution distributions. In this work we introduce a novel theoretical framework for analyzing the effectiveness of such methods. We ask whether there exist generative models that (i) are expressive enough to generate approximately optimal solutions; (ii) have a tractable, i.e, polynomial in the size of the input, number of parameters; (iii) their optimization landscape is benign in the sense that it does not contain sub-optimal stationary points. Our main contribution is a positive answer to this question. Our result holds for a broad class of combinatorial problems including Max- and Min-Cut, Max-$k$-CSP, Maximum-Weight-Bipartite-Matching, and the Traveling Salesman Problem. As a byproduct of our analysis we introduce a novel regularization process over vanilla gradient descent and provide theoretical and experimental evidence that it helps address vanishing-gradient issues and escape bad stationary points.
Quality of Service (QoS) prediction is an essential task in recommendation systems, where accurately predicting unknown QoS values can improve user satisfaction. However, existing QoS prediction techniques may perform poorly in the presence of noise data, such as fake location information or virtual gateways. In this paper, we propose the Probabilistic Deep Supervision Network (PDS-Net), a novel framework for QoS prediction that addresses this issue. PDS-Net utilizes a Gaussian-based probabilistic space to supervise intermediate layers and learns probability spaces for both known features and true labels. Moreover, PDS-Net employs a condition-based multitasking loss function to identify objects with noise data and applies supervision directly to deep features sampled from the probability space by optimizing the Kullback-Leibler distance between the probability space of these objects and the real-label probability space. Thus, PDS-Net effectively reduces errors resulting from the propagation of corrupted data, leading to more accurate QoS predictions. Experimental evaluations on two real-world QoS datasets demonstrate that the proposed PDS-Net outperforms state-of-the-art baselines, validating the effectiveness of our approach.
Control techniques like MPC can realize contact-rich manipulation which exploits dynamic information, maintaining friction limits and safety constraints. However, contact geometry and dynamics are required to be known. This information is often extracted from CAD, limiting scalability and the ability to handle tasks with varying geometry. To reduce the need for a priori models, we propose a framework for estimating contact models online based on torque and position measurements. To do this, compliant contact models are used, connected in parallel to model multi-point contact and constraints such as a hinge. They are parameterized to be differentiable with respect to all of their parameters (rest position, stiffness, contact location), allowing the coupled robot/environment dynamics to be linearized or efficiently used in gradient-based optimization. These models are then applied for: offline gradient-based parameter fitting, online estimation via an extended Kalman filter, and online gradient-based MPC. The proposed approach is validated on two robots, showing the efficacy of sensorless contact estimation and the effects of online estimation on MPC performance.
Deep learning based techniques have been popularly adopted in acoustic echo cancellation (AEC). Utilization of speaker representation has extended the frontier of AEC, thus attracting many researchers' interest in personalized acoustic echo cancellation (PAEC). Meanwhile, task-decoupling strategies are widely adopted in speech enhancement. To further explore the task-decoupling approach, we propose to use a two-stage task-decoupling post-filter (TDPF) in PAEC. Furthermore, a multi-scale local-global speaker representation is applied to improve speaker extraction in PAEC. Experimental results indicate that the task-decoupling model can yield better performance than a single joint network. The optimal approach is to decouple the echo cancellation from noise and interference speech suppression. Based on the task-decoupling sequence, optimal training strategies for the two-stage model are explored afterwards.
We introduce a wearable single-eye emotion recognition device and a real-time approach to recognizing emotions from partial observations of an emotion that is robust to changes in lighting conditions. At the heart of our method is a bio-inspired event-based camera setup and a newly designed lightweight Spiking Eye Emotion Network (SEEN). Compared to conventional cameras, event-based cameras offer a higher dynamic range (up to 140 dB vs. 80 dB) and a higher temporal resolution. Thus, the captured events can encode rich temporal cues under challenging lighting conditions. However, these events lack texture information, posing problems in decoding temporal information effectively. SEEN tackles this issue from two different perspectives. First, we adopt convolutional spiking layers to take advantage of the spiking neural network's ability to decode pertinent temporal information. Second, SEEN learns to extract essential spatial cues from corresponding intensity frames and leverages a novel weight-copy scheme to convey spatial attention to the convolutional spiking layers during training and inference. We extensively validate and demonstrate the effectiveness of our approach on a specially collected Single-eye Event-based Emotion (SEE) dataset. To the best of our knowledge, our method is the first eye-based emotion recognition method that leverages event-based cameras and spiking neural network.
The three-dimensional reconstruction of vocal folds in medicine usually involves endoscopy and an approach to extract depth information like structured light or stereo matching of images. The resulting mesh can accurately represent the superior area of the vocal folds, while new approaches also try to reconstruct the inferior area. We propose a novel approach to extract the time-dependent 3D geometry of the vocal fold from optical measurements on both the superior and inferior side, requiring optical measurements only from the superior side. First, a time-dependent, tri-variate surface velocity vector field is reconstructed using a high-speed camera and a laser Doppler vibrometer in an experimental environment. This vector field serves as target in an inverse finite-element simulation that optimizes the forces applied to a deformable vocal fold model such that the resulting movement after FEM simulation matches the velocity observations on the superior side. The required forces for the finite element method simulation are treated as unknowns and are assembled using multiple scalar fields. We use tensor products in B\'ezier Bernstein basis for our scalar fields to reduce the degrees of freedom for our optimization. We use gradient descent to optimize the control points of the force field polynomials. Our utilized error metric for gradient descent consists of two terms. The first term is used to match the simulated velocities to the observed measurements, while the second term measures the silhouette difference between observation and simulation.
Simulation-based inference (SBI) methods such as approximate Bayesian computation (ABC), synthetic likelihood, and neural posterior estimation (NPE) rely on simulating statistics to infer parameters of intractable likelihood models. However, such methods are known to yield untrustworthy and misleading inference outcomes under model misspecification, thus hindering their widespread applicability. In this work, we propose the first general approach to handle model misspecification that works across different classes of SBI methods. Leveraging the fact that the choice of statistics determines the degree of misspecification in SBI, we introduce a regularized loss function that penalises those statistics that increase the mismatch between the data and the model. Taking NPE and ABC as use cases, we demonstrate the superior performance of our method on high-dimensional time-series models that are artificially misspecified. We also apply our method to real data from the field of radio propagation where the model is known to be misspecified. We show empirically that the method yields robust inference in misspecified scenarios, whilst still being accurate when the model is well-specified.
While significant progress has been made on Physics-Informed Neural Networks (PINNs), a comprehensive comparison of these methods across a wide range of Partial Differential Equations (PDEs) is still lacking. This study introduces PINNacle, a benchmarking tool designed to fill this gap. PINNacle provides a diverse dataset, comprising over 20 distinct PDEs from various domains, including heat conduction, fluid dynamics, biology, and electromagnetics. These PDEs encapsulate key challenges inherent to real-world problems, such as complex geometry, multi-scale phenomena, nonlinearity, and high dimensionality. PINNacle also offers a user-friendly toolbox, incorporating about 10 state-of-the-art PINN methods for systematic evaluation and comparison. We have conducted extensive experiments with these methods, offering insights into their strengths and weaknesses. In addition to providing a standardized means of assessing performance, PINNacle also offers an in-depth analysis to guide future research, particularly in areas such as domain decomposition methods and loss reweighting for handling multi-scale problems and complex geometry. To the best of our knowledge, it is the largest benchmark with a diverse and comprehensive evaluation that will undoubtedly foster further research in PINNs.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191