Related papers: High-Fidelity Audio Generation and Representation …

Human computer interaction (HCI) involves a multidisciplinary fusion of technologies, through which the control of external devices could be achieved by monitoring physiological status of users. However, physiological biosignals often vary…

The central question in representation learning is what constitutes a good or meaningful representation. In this work we argue that if we consider data with inherent cluster structures, where clusters can be characterized through different…

Graphs are ubiquitous in real-world scenarios and encompass a diverse range of tasks, from node-, edge-, and graph-level tasks to transfer learning. However, designing specific tasks for each type of graph data is often costly and lacks…

Recently, encoder-decoder neural models have achieved great success on text generation tasks. However, one problem of this kind of models is that their performances are usually limited by the scale of well-labeled data, which are very…

The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we…

Advancing defensive mechanisms against adversarial attacks in generative models is a critical research topic in machine learning. Our study focuses on a specific type of generative models - Variational Auto-Encoders (VAEs). Contrary to…

We present the development of a semi-supervised regression method using variational autoencoders (VAE), which is customized for use in soft sensing applications. We motivate the use of semi-supervised learning considering the fact that…

The Variational Autoencoder (VAE) is a seminal approach in deep generative modeling with latent variables. Interpreting its reconstruction process as a nonlinear transformation of samples from the latent posterior distribution, we apply the…

We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also…

Disentangled sequential autoencoders (DSAEs) represent a class of probabilistic graphical models that describes an observed sequence with dynamic latent variables and a static latent variable. The former encode information at a frame rate…

Multiple modalities often co-occur when describing natural phenomena. Learning a joint representation of these modalities should yield deeper and more useful representations. Previous generative approaches to multi-modal input either do not…

Wasserstein autoencoders are effective for text generation. They do not however provide any control over the style and topic of the generated sentences if the dataset has multiple classes and includes different topics. In this work, we…

Learning disentanglement aims at finding a low dimensional representation which consists of multiple explanatory and generative factors of the observational data. The framework of variational autoencoder (VAE) is commonly used to…

This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is…

Recent work (Bengio et al., 2013) has shown howDenoising Auto-Encoders(DAE) become gener-ative models as a density estimator. However,in practice, the framework suffers from a mixingproblem in the MCMC sampling process and nodirect method…

Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework. However, only a…

Deep generative models often perform poorly in real-world applications due to the heterogeneity of natural data sets. Heterogeneity arises from data containing different types of features (categorical, ordinal, continuous, etc.) and…

We propose a semi-supervised approach to acoustic source localization in reverberant environments based on deep generative modeling. Localization in reverberant environments remains an open challenge. Even with large data volumes, the…

Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the variational cost…

Deep generative models have been demonstrated as problematic in the unsupervised out-of-distribution (OOD) detection task, where they tend to assign higher likelihoods to OOD samples. Previous studies on this issue are usually not…