Acoustic Modeling Using Deep Belief Networks

@article{Mohamed2012AcousticMU,
  title={Acoustic Modeling Using Deep Belief Networks},
  author={Abdel-rahman Mohamed and George E. Dahl and Geoffrey E. Hinton},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2012},
  volume={20},
  pages={14-22}
}
Gaussian mixture models are currently the dominant technique for modeling the emission distribution of hidden Markov models for speech recognition. We show that better phone recognition on the TIMIT dataset can be achieved by replacing Gaussian mixture models by deep neural networks that contain many layers of features and a very large number of parameters. These networks are first pre-trained as a multi-layer generative model of a window of spectral feature vectors without making use of any… Expand
1,554 Citations
Deep Belief Networks using discriminative features for phone recognition
  • 282
  • PDF
A critical examination of deep learningapproaches to automated speech recognition
Understanding how Deep Belief Networks perform acoustic modelling
  • 277
  • PDF
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
  • 6,565
  • PDF
Implementation of DNN-HMM Acoustic Models for Phoneme Recognition
  • 5
  • Highly Influenced
Speech recognition features based on deep latent Gaussian models
Acoustic Modeling Based on Deep Conditional Random Fields
  • PDF
Restructuring output layers of deep neural networks using minimum risk parameter clustering
  • 1
  • PDF
Modular combination of deep neural networks for acoustic modeling
  • 35
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 64 REFERENCES
Investigation of full-sequence training of deep belief networks for speech recognition
  • 212
  • PDF
Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition
  • 2,498
  • PDF
Speech Recognition Using Augmented Conditional Random Fields
  • 92
  • PDF
Speaker-independent phone recognition using hidden Markov models
  • K. Lee, H. Hon
  • Computer Science
  • IEEE Trans. Acoust. Speech Signal Process.
  • 1989
  • 1,014
  • PDF
Large Margin Gaussian Mixture Modeling for Phonetic Classification and Recognition
  • Fei Sha, L. Saul
  • Computer Science
  • 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings
  • 2006
  • 158
  • PDF
A Fast Learning Algorithm for Deep Belief Nets
  • 11,871
  • PDF
Use of Differential Cepstra as Acoustic Features in Hidden Trajectory Modeling for Phonetic Recognition
  • L. Deng, Dong Yu
  • Computer Science
  • 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07
  • 2007
  • 53
  • PDF
The acoustic-modeling problem in automatic speech recognition
  • 272
  • PDF
Structured speech modeling
  • 93
  • PDF
...
1
2
3
4
5
...