A hierarchical context dependent neural network architecture for improved phone recognition

a hierarchical context dependent neural network architecture for improved phone recognition.pdf Download this file

This paper explored the CD phone recognition on TIMIT using hybrid NN/HMM system. 

1) Using two nets in tandem, one for CI posteriors and the other modeling the contexts from the CI posteriors;

2) Directly train a NN for CD state posteriors, too many outputs and not robust;

3) The first net is to give bottleneck features and then use another net on top of it.

The best results on TIMIT is 21.24% on core test set, there is less than 1% difference from the DBN based monophone recognition, thus rendering the context gain not significant. And also using DBN, the current best results is around 19%. 

Posted via email from Troy's posterous