A deep architecture with bilinear modeling of hidden representations: Applications to phonetic recognition

Brian Hutchinson, Li Deng, Dong Yu

Abstract

We develop and describe a novel deep architecture, the Tensor Deep Stacking Network (T-DSN), where multiple blocks are stacked one on top of another and where a bilinear mapping from hidden representations to the output in each block is used to incorporate higher-order statistics of the input features. A learning algorithm for the T-DSN is presented, in which the main parameter estimation burden is shifted to a convex sub-problem with a closed-form solution. Using an efficient and scalable parallel implementation, we train a T-DSN to discriminate standard three-state monophones in the TIMIT database. The T-DSN outperforms an alternative pretrained Deep Neural Network (DNN) architecture in frame-level classification (both state and phone) and in the cross-entropy measure. For continuous phonetic recognition, T-DSN performs equivalently to a DNN but without the need for a hard-to-scale, sequential fine-tuning step.
BibTeX
@inproceedings{hutchinson2012deep,
  author = {Brian Hutchinson and Li Deng and Dong Yu},
  title = {{A deep architecture with bilinear modeling of hidden representations: Applications to phonetic recognition}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2012},
  doi = {10.1109/icassp.2012.6288994},
}

Loading related content...

Figure