Multi-View and Multi-Objective Semi-Supervised Learning for HMM-Based Automatic Speech Recognition

@article{Cui2012MultiViewAM,
  title={Multi-View and Multi-Objective Semi-Supervised Learning for HMM-Based Automatic Speech Recognition},
  author={Xiaodong Cui and Jing Huang and Jen-Tzung Chien},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2012},
  volume={20},
  pages={1923-1935}
}
Current hidden Markov acoustic modeling for large-vocabulary continuous speech recognition (LVCSR) heavily relies on the availability of abundant labeled transcriptions. Given that speech labeling is both expensive and time-consuming while there is a huge amount of unlabeled data easily available nowadays, the semi-supervised learning (SSL) from both labeled and unlabeled data aiming to reduce the development cost for LVCSR becomes more important than ever. In this paper, a new SSL approach is… CONTINUE READING
Highly Cited
This paper has 34 citations. REVIEW CITATIONS
18 Citations
46 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 18 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 46 references

Cross-view transfer learning for automatic speech recognition

  • J. Huang, X. Cui, J.-T. Chien
  • Proc. NIPS 2010 Workshop Transfer Learn. by Learn…
  • 2010
1 Excerpt

Similar Papers

Loading similar papers…