Deep convolutional neural networks for LVCSR

@article{Sainath2013DeepCN,
  title={Deep convolutional neural networks for LVCSR},
  author={T. Sainath and Abdel-rahman Mohamed and Brian Kingsbury and B. Ramabhadran},
  journal={2013 IEEE International Conference on Acoustics, Speech and Signal Processing},
  year={2013},
  pages={8614-8618}
}
  • T. Sainath, Abdel-rahman Mohamed, +1 author B. Ramabhadran
  • Published 2013
  • Computer Science
  • 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
  • Convolutional Neural Networks (CNNs) are an alternative type of neural network that can be used to reduce spectral variations and model spectral correlations which exist in signals. [...] Key Method Specifically, we focus on how many convolutional layers are needed, what is the optimal number of hidden units, what is the best pooling strategy, and the best input feature type for CNNs. We then explore the behavior of neural network features extracted from CNNs on a variety of LVCSR tasks, comparing CNNs to DNNs…Expand Abstract
    821 Citations

    Figures, Tables, and Topics from this paper.

    Deep Convolutional Neural Networks for Large-scale Speech Tasks
    • 323
    Improvements to Deep Convolutional Neural Networks for LVCSR
    • 168
    • PDF
    Very deep multilingual convolutional neural networks for LVCSR
    • 176
    • PDF
    An analysis of convolutional neural networks for speech recognition
    • Jui-Ting Huang, J. Li, Y. Gong
    • Computer Science
    • 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2015
    • 79
    • PDF
    Very deep convolutional neural networks for LVCSR
    • 58
    • Highly Influenced
    • PDF
    Phone recognition with hierarchical convolutional deep maxout networks
    • L. Tóth
    • Computer Science
    • EURASIP J. Audio Speech Music. Process.
    • 2015
    • 77
    • PDF
    Convolutional Neural Networks for Speech Recognition
    • 1,139
    • PDF
    A Hybrid of Deep CNN and Bidirectional LSTM for Automatic Speech Recognition
    • 7
    • Highly Influenced
    • PDF
    Advances in Very Deep Convolutional Neural Networks for LVCSR
    • 41
    • PDF
    Convolutional Neural Network for ASR
    • Sourav Newatia, R. K. Aggarwal
    • Computer Science
    • 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA)
    • 2018
    • 2

    References

    SHOWING 1-10 OF 17 REFERENCES
    Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition
    • 705
    • PDF
    Application of Pretrained Deep Neural Networks to Large Vocabulary Speech Recognition
    • 226
    • PDF
    Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition
    • 2,422
    • PDF
    Face recognition: a convolutional neural-network approach
    • 2,197
    • PDF
    Deep Neural Networks for Acoustic Modeling in Speech Recognition
    • 2,003
    • PDF
    Auto-encoder bottleneck features using deep belief networks
    • 168
    • PDF
    Making Deep Belief Networks effective for large vocabulary continuous speech recognition
    • 189
    • PDF
    Scalable Minimum Bayes Risk Training of Deep Neural Network Acoustic Models Using Distributed Hessian-free Optimization
    • 231
    • PDF
    Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling
    • Brian Kingsbury
    • Computer Science
    • 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
    • 2009
    • 279
    • PDF