Phone sequence modeling with recurrent neural networks

Nicolas Boulanger-Lewandowski, Jasha Droppo, Mike Seltzer, Dong Yu

Abstract

In this paper, we investigate phone sequence modeling with recurrent neural networks in the context of speech recognition. We introduce a hybrid architecture that combines a phonetic model with an arbitrary frame-level acoustic model and we propose efficient algorithms for training, decoding and sequence alignment. We evaluate the advantage of our phonetic model on the TIMIT and Switchboard-mini datasets in complementarity to a powerful context-dependent deep neural network (DNN) acoustic classifier and a higher-level 3-gram language model. Consistent improvements of 2-10% in phone accuracy and 3% in word error rate suggest that our approach can readily replace HMMs in current state-of-the-art systems.
BibTeX
@inproceedings{boulangerlewandowski2014phone,
  author = {Nicolas Boulanger-Lewandowski and Jasha Droppo and Mike Seltzer and Dong Yu},
  title = {{Phone sequence modeling with recurrent neural networks}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2014},
  doi = {10.1109/icassp.2014.6854638},
}

Loading related content...

Figure