Projects per year
Abstract / Description of output
Artificial neural networks (ANN) have proven to be well suited to the task of articulatory feature (AF) recognition. Previous studies have taken a cascaded approach where separate ANNs are trained for each feature group, making the assumption that features are 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.
|Title of host publication||Interspeech 2005 - Eurospeech|
|Subtitle of host publication||9th European Conference on Speech Communication and Technology|
|Publisher||International Speech Communication Association|
|Number of pages||4|
|Publication status||Published - 1 Sept 2005|
FingerprintDive into the research topics of 'A Hybrid ANN/DBN Approach to Articulatory Feature Recognition'. Together they form a unique fingerprint.
- 4 Finished
1/01/05 → 31/12/09