Advanced search
1 file | 800.95 KB

Phoneme recognition with large hierarchical reservoirs

Author
Organization
Project
ORGANIC (Self-organized recurrent neural learning for language processing)
Abstract
Automatic speech recognition has gradually improved over the years, but the reliable recognition of unconstrained speech is still not within reach. In order to achieve a breakthrough, many research groups are now investigating new methodologies that have potential to outperform the Hidden Markov Model technology that is at the core of all present commercial systems. In this paper, it is shown that the recently introduced concept of Reservoir Computing might form the basis of such a methodology. In a limited amount of time, a reservoir system that can recognize the elementary sounds of continuous speech has been built. The system already achieves a state-of-the-art performance, and there is evidence that the margin for further improvements is still significant.
Keywords
Reservoir Computing, Echo State Networks, Speech, Phoneme Recognition, Neural Networks, Phone Recognition

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 800.95 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Triefenbach, Fabian, Azarakhsh Jalalvand, Benjamin Schrauwen, and Jean-Pierre Martens. 2010. “Phoneme Recognition with Large Hierarchical Reservoirs.” In Advances in Neural Information Processing Systems, ed. J Lafferty, CKI Williams, J Shawe-Taylor, RS Zemel, and A Culotta. Vol. 23. Neural Information Processing System Foundation.
APA
Triefenbach, F., Jalalvand, A., Schrauwen, B., & Martens, J.-P. (2010). Phoneme recognition with large hierarchical reservoirs. In J. Lafferty, C. Williams, J. Shawe-Taylor, R. Zemel, & A. Culotta (Eds.), Advances in Neural Information Processing Systems (Vol. 23). Presented at the 24th Annual conference on Neural Information Processing Systems (NIPS 2010), Neural Information Processing System Foundation.
Vancouver
1.
Triefenbach F, Jalalvand A, Schrauwen B, Martens J-P. Phoneme recognition with large hierarchical reservoirs. In: Lafferty J, Williams C, Shawe-Taylor J, Zemel R, Culotta A, editors. Advances in Neural Information Processing Systems. Neural Information Processing System Foundation; 2010.
MLA
Triefenbach, Fabian, Azarakhsh Jalalvand, Benjamin Schrauwen, et al. “Phoneme Recognition with Large Hierarchical Reservoirs.” Advances in Neural Information Processing Systems. Ed. J Lafferty et al. Vol. 23. Neural Information Processing System Foundation, 2010. Print.
@inproceedings{1094421,
  abstract     = {Automatic speech recognition has gradually improved over the years, but the reliable recognition of unconstrained speech is still not within reach. In order to achieve a breakthrough, many research groups are now investigating new methodologies that have potential to outperform the Hidden Markov Model technology that is at the core of all present commercial systems. In this paper, it is shown that the recently introduced concept of Reservoir Computing might form the basis of such a methodology. In a limited amount of time, a reservoir system that can recognize the elementary sounds of continuous speech has been built. The system already achieves a state-of-the-art performance, and there is evidence that the margin for further improvements is still significant.},
  author       = {Triefenbach, Fabian and Jalalvand, Azarakhsh and Schrauwen, Benjamin and Martens, Jean-Pierre},
  booktitle    = {Advances in Neural Information Processing Systems},
  editor       = {Lafferty, J and Williams, CKI and Shawe-Taylor, J and Zemel, RS and Culotta, A},
  issn         = {1049-5258},
  keyword      = {Reservoir Computing,Echo State Networks,Speech,Phoneme Recognition,Neural Networks,Phone Recognition},
  language     = {eng},
  location     = {Vancouver, BC, Canada},
  pages        = {9},
  publisher    = {Neural Information Processing System Foundation},
  title        = {Phoneme recognition with large hierarchical reservoirs},
  url          = {http://books.nips.cc/papers/files/nips23/NIPS2010\_0760.pdf},
  volume       = {23},
  year         = {2010},
}