Corpus ID: 216650891

Training log-linear acoustic models in higher-order polynomial feature space for speech recognition

@inproceedings{Tahir2013TrainingLA,
  title={Training log-linear acoustic models in higher-order polynomial feature space for speech recognition},
  author={M. Tahir and H. Huang and R. Schl{\"u}ter and H. Ney and L. Bosch and B. Cranen and L. Boves},
  booktitle={INTERSPEECH},
  year={2013}
}
  • M. Tahir, H. Huang, +4 authors L. Boves
  • Published in INTERSPEECH 2013
  • Computer Science
    • 14th Annual Conference of the International Speech Communication Association, 25 augustus 2013 
    View Paper
    www-i6.informatik.rwth-aachen.de
    3 Citations

    Figures, Tables, and Topics from this paper

    Figures and Tables

    Explore Further: Topics Discussed in This Paper

    3 Citations
    Citation Type

    Citation Type

    Training of reduced-rank linear transformations for multi-layer polynomial acoustic features for speech recognition
    • 1
    • PDF
    Discriminative training of linear transformations and mixture density splitting for speech recognition
    • PDF
    Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables
    • 29
    • PDF

    References

    SHOWING 1-10 OF 10 REFERENCES
    Log-Linear Framework for Linear Feature Transformations in Speech Recognition
    • 9
    • Highly Influential
    • PDF
    Log-Linear Optimization of Second-Order Polynomial Features with Subsequent Dimension Reduction for Speech Recognition
    • 5
    • Highly Influential
    • PDF
    Investigations on features for log-linear acoustic models in continuous speech recognition
    • 22
    • PDF
    Feature selection for log-linear acoustic models
    • 7
    • PDF
    A log-linear discriminative modeling framework for speech recognition
    • 43
    • Highly Influential
    • PDF
    Knowledge-based Quadratic Discriminant Analysis for phonetic classification
    • 2
    Subspace pursuit method for kernel-log-linear models
    • Y. Kubo, Simon Wiesler, +4 authors T. Kobayashi
    • Mathematics, Computer Science
    • 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2011
    • 6
    • PDF
    Latent Log-Linear Models for Handwritten Digit Classification
    • 20
    • PDF
    On the use of support vector machines for phonetic classification
    • P. Clarkson, P. Moreno
    • Computer Science
    • 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)
    • 1999
    • 198
    • PDF
    An overview of statistical learning theory
    • V. Vapnik
    • Computer Science, Medicine
    • IEEE Trans. Neural Networks
    • 1999
    • 4,194
    • PDF