Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

@article{Hinton2012DeepNN,
  title={Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups},
  author={Geoffrey E. Hinton and L. Deng and Dong Yu and G. Dahl and Abdel-rahman Mohamed and Navdeep Jaitly and A. Senior and V. Vanhoucke and Patrick Nguyen and T. Sainath and Brian Kingsbury},
  journal={IEEE Signal Processing Magazine},
  year={2012},
  volume={29},
  pages={82-97}
}
  • Geoffrey E. Hinton, L. Deng, +8 authors Brian Kingsbury
  • Published 2012
  • Computer Science
  • IEEE Signal Processing Magazine
  • Most current speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well each state of each HMM fits a frame or a short window of frames of coefficients that represents the acoustic input. An alternative way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural… CONTINUE READING
    6,125 Citations
    Noise Robust Speech Recognition Using Deep Belief Networks
    • 3
    Deep neural networks with auxiliary Gaussian mixture models for real-time speech recognition
    • 18
    Deep segmental neural networks for speech recognition
    • 39
    • PDF
    Convolutional Neural Networks for Speech Recognition
    • 1,131
    • PDF
    Deep neural networks employing Multi-Task Learning and stacked bottleneck features for speech synthesis
    • 226
    • PDF
    A Study of the Recurrent Neural Network Encoder-Decoder for Large Vocabulary Speech Recognition
    • 52
    • PDF
    Acoustic modeling in Automatic Speech Recognition - A Survey
    • A. Waris, R. K. Aggarwal
    • Computer Science
    • 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA)
    • 2018
    • 1

    References

    SHOWING 1-10 OF 74 REFERENCES
    Deep Belief Networks using discriminative features for phone recognition
    • 276
    • PDF
    Acoustic Modeling Using Deep Belief Networks
    • 1,502
    • PDF
    Deep Belief Networks for phone recognition
    • 357
    • PDF
    Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition
    • 2,420
    • PDF
    Speech Recognition Using Augmented Conditional Random Fields
    • 92
    • 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
    • 276
    • PDF
    Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition
    • 701
    • PDF
    Tandem connectionist feature extraction for conventional HMM systems
    • H. Hermansky, D. Ellis, S. Sharma
    • Computer Science
    • 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)
    • 2000
    • 787
    • PDF