Learning deep autoregressive models for hierarchical data
This addresses efficient modeling of complex sequential data like speech and text, though it appears incremental as an extension of existing methods.
The authors tackled modeling hierarchical structured data by extending stochastic temporal convolutional networks with an autoregressive model and hierarchical variational autoencoder, achieving state-of-the-art performance on speech and handwritten text data.
We propose a model for hierarchical structured data as an extension to the stochastic temporal convolutional network. The proposed model combines an autoregressive model with a hierarchical variational autoencoder and downsampling to achieve superior computational complexity. We evaluate the proposed model on two different types of sequential data: speech and handwritten text. The results are promising with the proposed model achieving state-of-the-art performance.