ISCA Archive Interspeech 2014
ISCA Archive Interspeech 2014

Asynchronous, online, GMM-free training of a context dependent acoustic model for speech recognition

Michiel Bacchiani, Andrew Senior, Georg Heigold

We propose an algorithm that allows online training of a context dependent DNN model. It designs a state inventory based on DNN features and jointly optimizes the DNN parameters and alignment of the training data. The process allows flat starting a model from scratch and avoids any dependency on a GMM acoustic model to bootstrap the training process. A 15k state model trained with the proposed algorithm reduced the error rate on a mobile speech task by 24% compared to a system bootstrapped from a CI GMM and by 16% compared to a system bootstrapped from a CD GMM system.


doi: 10.21437/Interspeech.2014-430

Cite as: Bacchiani, M., Senior, A., Heigold, G. (2014) Asynchronous, online, GMM-free training of a context dependent acoustic model for speech recognition. Proc. Interspeech 2014, 1900-1904, doi: 10.21437/Interspeech.2014-430

@inproceedings{bacchiani14_interspeech,
  author={Michiel Bacchiani and Andrew Senior and Georg Heigold},
  title={{Asynchronous, online, GMM-free training of a context dependent acoustic model for speech recognition}},
  year=2014,
  booktitle={Proc. Interspeech 2014},
  pages={1900--1904},
  doi={10.21437/Interspeech.2014-430},
  issn={2308-457X}
}