Sequential Neural Models With Stochastic Layers

Abstract

How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue a deterministic recurrent neural network and a state space model together to form a stochastic and sequential neural generative model. The clear separation of deterministic and stochastic layers allows a structured variational inference network to track the factorization of the model's posterior distribution. By retaining both the nonlinear recursive structure of a recurrent neural network and averaging over the uncertainty in a latent path, like a state space model, we improve the state of the art results on the Blizzard and TIMIT speech modeling data sets by a large margin, while achieving comparable performances to competing methods on polyphonic music modeling.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfraccaro2016sequential

Related papers

• Stochastic Wavenet: A Generative Latent Variable Model For Sequential Data (2018)0.00
• Re-examination Of The Role Of Latent Variables In Sequence Modeling (2019)0.00
• Regularized Sequential Latent Variable Models With Adversarial Neural Networks (2021)2.26
• Rethinking Recurrent Latent Variable Model For Music Composition (2018)7.50
• Understanding Recurrent Neural State Using Memory Signatures (2018)0.00
• Utterance-level Sequential Modeling For Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit (2020)4.52
• Learning Waveform-based Acoustic Models Using Deep Variational Convolutional Neural Networks (2019)6.77
• Benchmarking Generative Latent Variable Models For Speech (2022)0.00