Recent advances in automatic speech recognition have used
large corpora and powerful computational resources to train
complex statistical models from high-dimensional features, to
attempt to capture all the variability found in natural speech.
Such models are difficult to interpret and may be fragile, and
contradict or ignore knowledge of human speech produc-
tion and perception. We report progress towards phoneme
recognition using a model of speech which employs very few
parameters and which is more faithful to the dynamics and
model of human speech production. Using features generated
from a neural network bottleneck layer, we obtain recognition
accuracy on TIMIT which compares favourably with tradi-
tional models of similar power. We discuss the implications
of these results for recognition using natural features such as
vocal tract resonances and spectral energies.