Interspeech'2005 - Eurospeech
Artificial neural networks (ANN) have proven to be well suited to the task of articulatory feature (AF) recognition. However, one drawback with an ANN approach is that features are assumed to be statistically independent. We address this by using ANNs to provide virtual evidence to a dynamic Bayesian network (DBN). This gives a hybrid ANN/DBN model and allows modelling of inter-feature dependencies. We demonstrate significant increases in AF recognition accuracy from modelling dependencies between features, and present the results of embedded training experiments in which a set of asynchronous feature changes are learned. Furthermore, we report on the application of a Viterbi training scheme in which we alternate between realigning the AF training labels and retraining the ANNs.
Bibliographic reference. Frankel, Joe / King, Simon (2005): "A hybrid ANN/DBN approach to articulatory feature recognition", In INTERSPEECH-2005, 3045-3048.