Radmm : Recurrent Adaptive Mixture Model with Applications to Domain Robust Language Modeling

@inproceedings{Irie2018RadmmR,
  title={Radmm : Recurrent Adaptive Mixture Model with Applications to Domain Robust Language Modeling},
  author={Kazuki Irie and Shankar Kumar and Michael Nirschl and Hank Liao},
  year={2018}
}
We present a new architecture and a training strategy for an adaptive mixture of experts with applications to domain robust language modeling. The proposed model is designed to benefit from the scenario where the training data are available in diverse domains as is the case for YouTube speech recognition. The two core components of our model are an ensemble… CONTINUE READING