A Hierarchy of Recurrent Networks for Speech Recognition

Generative models for sequential data based on directed graphs of Restricted Boltzmann Machines (RBMs) are able to accurately model high dimensional sequences as recently shown. In these models, temporal dependencies in the input are discovered by either buffering previous visible variables or by recurrent connections of the hidden variables. Here we propose a modification of these models, the Temporal Reservoir Machine (TRM). It utilizes a recurrent artificial neural network (ANN) for integrating information from the input over time. This information is then fed into a RBM at each time step. To avoid difficulties of recurrent network learning, the ANN remains untrained and hence can be thought of as a random feature extractor. Using the architecture of multi-layer RBMs (Deep Belief Networks), the TRMs can be used as a building block for complex hierarchical models. This approach unifies RBM-based approaches for sequential data modeling and the Echo State Network, a powerful approach for black-box system identification. The TRM is tested on a spoken digits task under noisy conditions, and competitive performances compared to previous models are observed.