Regularized Sequential Latent Variable Models With Adversarial Neural Networks

Abstract

The recurrent neural networks (RNN) with richly distributed internal states and flexible non-linear transition functions, have overtaken the dynamic Bayesian networks such as the hidden Markov models (HMMs) in the task of modeling highly structured sequential data. These data, such as from speech and handwriting, often contain complex relationships between the underlaying variational factors and the observed data. The standard RNN model has very limited randomness or variability in its structure, coming from the output conditional probability model. This paper will present different ways of using high level latent random variables in RNN to model the variability in the sequential data, and the training method of such RNN model under the VAE (Variational Autoencoder) principle. We will explore possible ways of using adversarial method to train a variational RNN model. Contrary to competing approaches, our approach has theoretical optimum in the model training and provides better model t

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyhuang2021regularized

Related papers

• Re-examination Of The Role Of Latent Variables In Sequence Modeling (2019)0.00
• Sequential Neural Models With Stochastic Layers (2016)0.00
• Stochastic Wavenet: A Generative Latent Variable Model For Sequential Data (2018)0.00
• Disentangled Sequential Autoencoder (2018)0.00
• A Recurrent Variational Autoencoder For Speech Enhancement (2019)13.97
• Switching Variational Auto-encoders For Noise-agnostic Audio-visual Speech Enhancement (2021)7.16
• A Bayesian Permutation Training Deep Representation Learning Method For Speech Enhancement With Variational Autoencoder (2022)7.16
• A Comparison Of Adaptation Techniques And Recurrent Neural Network Architectures (2018)3.58