Multilingual deep neural network based acoustic modeling for rapid language adaptation

Ngoc Thang Vu, David Imseng, Daniel Povey, Petr Motlícek, Tanja Schultz, Hervé BourlardICASSP 2014 · OpenReview

Abstract

This paper presents a study on multilingual deep neural network (DNN) based acoustic modeling and its application to new languages. We investigate the effect of phone merging on multilingual DNN in context of rapid language adaptation. Moreover, the combination of multilingual DNNs with Kullback-Leibler divergence based acoustic modeling (KL-HMM) is explored. Using ten different languages from the Globalphone database, our studies reveal that crosslingual acoustic model transfer through multilingual DNNs is superior to unsupervised RBM pre-training and greedy layer-wise supervised training. We also found that KL-HMM based decoding consistently outperforms conventional hybrid decoding, especially in low-resource scenarios. Furthermore, the experiments indicate that multilingual DNN training equally benefits from simple phoneset concatenation and manually derived universal phonesets.
BibTeX
@inproceedings{vu2014multilingual,
  author = {Ngoc Thang Vu and David Imseng and Daniel Povey and Petr Motlícek and Tanja Schultz and Hervé Bourlard},
  title = {{Multilingual deep neural network based acoustic modeling for rapid language adaptation}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2014},
  url = {https://openreview.net/forum?id=CRgezbckBXo},
}

Loading related content...

Figure