Dynamic rate adaptation

We describe a technique for automatically adapting to the rate of an incoming signal. We first build a model of the signal using a recurrent network trained to predict the input at some delay, for a ‘typical’ rate of the signal. Then, fixing the weights of this network, we adapt the time constant t of the network using gradient descent, adapting the delay appropriately as well. We have found that on simple signals, the network adapts rapidly to new inputs varying in rate from being twice as fast as the original signal, down to ten times as slow. So far our results are based on linear rate changes. We discuss the possibilities of the application of this idea to speech.