Subspace Gaussian mixture model for computer-assisted language learning

Rong Tong, Boon Pang Lim, Nancy F. Chen, Bin Ma, Haizhou Li

Abstract

In computer-assisted language learning (CALL), speech data from non-native speakers are usually insufficient for acoustic modeling. Subspace Gaussian Mixture Models (SGMM) have been effective in training automatic speech recognition (ASR) systems with limited amounts of training data. Therefore, in this work, we propose to use SGMM to improve the fluency assessment performance. In particular, the contributions of this work are: (i) The proposed SGMM acoustic model trained with native data outperforms the MMI-GMM/HMM baseline by 25% relative, (ii) when incorporating a small amount of non-native training data, the SGMM acoustic model further improves the performance of fluency assessment by 47% relative.
BibTeX
@inproceedings{tong2014subspace,
  author = {Rong Tong and Boon Pang Lim and Nancy F. Chen and Bin Ma and Haizhou Li},
  title = {{Subspace Gaussian mixture model for computer-assisted language learning}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2014},
  doi = {10.1109/icassp.2014.6854624},
}

Loading related content...

Figure