Related papers: A Recurrent Variational Autoencoder for Speech Enh…

Recent language models can generate interesting and grammatically correct text in story generation but often lack plot development and long-term coherence. This paper experiments with a latent vector planning approach based on a TD-VAE…

Speech enhancement in hearing aids remains a difficult task in nonstationary acoustic environments, mainly because current signal processing algorithms rely on fixed, manually tuned parameters that cannot adapt in situ to different users or…

Recently, conditional score-based diffusion models have gained significant attention in the field of supervised speech enhancement, yielding state-of-the-art performance. However, these methods may face challenges when generalising to…

Deep generative neural networks, such as Variational AutoEncoders (VAEs), offer an opportunity to better understand and control language models from the perspective of sentence-level latent spaces. To combine the controllability of VAE…

Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…

Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular…

Variational auto-encoders (VAEs) provide an attractive solution to image generation problem. However, they tend to produce blurred and over-smoothed images due to their dependence on pixel-wise reconstruction loss. This paper introduces a…

In this paper, we propose a latent-variable generative model called mixture of dynamical variational autoencoders (MixDVAE) to model the dynamics of a system composed of multiple moving sources. A DVAE model is pre-trained on a…

In this paper we explore the effect of architectural choices on learning a Variational Autoencoder (VAE) for text generation. In contrast to the previously introduced VAE model for text where both the encoder and decoder are RNNs, we…

Variational autoencoders (VAE) represent a popular, flexible form of deep generative model that can be stochastically fit to samples from a given random process using an information-theoretic variational bound on the true underlying…

VAEs (Variational AutoEncoders) have proved to be powerful in the context of density modeling and have been used in a variety of contexts for creative purposes. In many settings, the data we model possesses continuous attributes that we…

This paper proposes VARA-TTS, a non-autoregressive (non-AR) text-to-speech (TTS) model using a very deep Variational Autoencoder (VDVAE) with Residual Attention mechanism, which refines the textual-to-acoustic alignment layer-wisely.…

Learning the latent representation of data in unsupervised fashion is a very interesting process that provides relevant features for enhancing the performance of a classifier. For speech emotion recognition tasks, generating effective…

Deep generative models are attracting great attention as a new promising approach for molecular design. All models reported so far are based on either variational autoencoder (VAE) or generative adversarial network (GAN). Here we propose a…

Advancement in speech technology has brought convenience to our life. However, the concern is on the rise as speech signal contains multiple personal attributes, which would lead to either sensitive information leakage or bias toward…

Audio-visual speech enhancement aims to extract clean speech from a noisy environment by leveraging not only the audio itself but also the target speaker's lip movements. This approach has been shown to yield improvements over audio-only…

This paper proposes a hierarchical generative model with a multi-grained latent variable to synthesize expressive speech. In recent years, fine-grained latent variables are introduced into the text-to-speech synthesis that enable the fine…

Recent state-of-the-art autoencoder based generative models have an encoder-decoder structure and learn a latent representation with a pre-defined distribution that can be sampled from. Implementing the encoder networks of these models in a…

We propose a topic-guided variational autoencoder (TGVAE) model for text generation. Distinct from existing variational autoencoder (VAE) based approaches, which assume a simple Gaussian prior for the latent code, our model specifies the…

Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures. However, applying similar methods to discrete structures,…