Multi-task learning strategies for a recurrent neural net in a hybrid tied-posteriors acoustic model

@inproceedings{Stadermann2005MultitaskLS,
  title={Multi-task learning strategies for a recurrent neural net in a hybrid tied-posteriors acoustic model},
  author={Jan Stadermann and Wolfram Koska and Gerhard Rigoll},
  booktitle={INTERSPEECH},
  year={2005}
}
An important goal of an automatic classifier is to learn the best possible generalization from given training material. One possible improvement over a standard learning algorithm is to train several related tasks in parallel. We apply the multi-task learning scheme to a recurrent neural network estimating phoneme posterior probabilities and HMM state posterior probabilities, respectively. A comparison of networks with different additional tasks within a hybrid NN/HMM acoustic model is… CONTINUE READING
Highly Cited
This paper has 26 citations. REVIEW CITATIONS