Better Generative Models for Sequential Data Problems: Bidirectional Recurrent Mixture Density Networks

By Mike Schuster. 1999

Subfields: Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

1. Justin Bayer
2. Christian Osendorfer
3. Yoshua Bengio
4. Alex Graves
5. Oriol Vinyals
6. Ruslan Salakhutdinov
7. Diederik P. Kingma
8. Aaron C. Courville

Citations in the corpus

• Generating Sequences With Recurrent Neural Networks (2013, background): “Mixture density outputs can also be used with recurrent neural networks [28].”
• A Vector Quantized Variational Autoencoder (VQ-VAE) Autoregressive Neural $F_0$ Model for Statistical Parametric Speech Synthesis (2020, unknown): “[32], [33] where the Gaussian distribution is replaced with a Gaussian mixture model (GMM).”
• Variational inference of latent state sequences using Recurrent Networks (2014, methodology): “e latent state sequences and the recognition model, as argued above. A suitable framework for mapping a sequence to another sequence of equal length is that of bidirectional recurrent neural networks [25] using fast dropout, which we employ in the generating and the recognition model. The computatio”