The Deep Tensor Neural Network With Applications to Large Vocabulary Speech Recognition

@article{Yu2013TheDT,
  title={The Deep Tensor Neural Network With Applications to Large Vocabulary Speech Recognition},
  author={Dong Yu and Li Deng and Frank Seide},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2013},
  volume={21},
  pages={388-396}
}
The recently proposed context-dependent deep neural network hidden Markov models (CD-DNN-HMMs) have been proved highly promising for large vocabulary speech recognition. In this paper, we develop a more advanced type of DNN, which we call the deep tensor neural network (DTNN). The DTNN extends the conventional DNN by replacing one or more of its layers with a double-projection (DP) layer, in which each input vector is projected into two nonlinear subspaces, and a tensor layer, in which two… CONTINUE READING

Figures, Tables, results, and Topics from this paper.

Key Quantitative Results

  • Evaluation on Switchboard tasks indicates that DTNNs can outperform the already high-performing DNNs with 4-5% and 3% relative word error reduction, respectively, using 30-hr and 309-hr training sets.

Citations

Publications citing this paper.
SHOWING 1-10 OF 60 CITATIONS, ESTIMATED 29% COVERAGE

FILTER CITATIONS BY YEAR

2012
2019

CITATION STATISTICS

  • 3 Highly Influenced Citations

  • Averaged 6 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 23 REFERENCES

Similar Papers

Loading similar papers…