A technique for adapting to speech rate

A technique is proposed for automatically estimating and dynamically adapting to the rate of a speech signal. A recurrent network is first trained to predict the input signal at a normal rate. Once trained, the network essentially becomes a model of the signal. Then, with the weights fixed, the network's time constant is adapted using gradient descent as it receives the same signal at a different rate. The network's time constant thus becomes a measure of the rate of the signal and can be used to drive the recognition process. Experiments show that, on simple signals, the network adapts rapidly to new inputs of varying rates. The results suggest that rapid adaptation to speaking rate can be accomplished by this method.<
>