Exploring how deep neural networks form phonemic categories

@inproceedings{Nagamine2015ExploringHD,
  title={Exploring how deep neural networks form phonemic categories},
  author={Tasha Nagamine and Michael L. Seltzer and Nima Mesgarani},
  booktitle={INTERSPEECH},
  year={2015}
}
Deep neural networks (DNNs) have become the dominant technique for acoustic-phonetic modeling due to their markedly improved performance over other models. Despite this, little is understood about the computation they implement in creating phonemic categories from highly variable acoustic signals. In this paper, we analyzed a DNN trained for phoneme recognition and characterized its representational properties, both at the single node and population level in each layer. At the single node level… CONTINUE READING
Highly Cited
This paper has 45 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 25 extracted citations

Cross-Entropy Training of DNN Ensemble Acoustic Models for Low-Resource ASR

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2018
View 2 Excerpts

References

Publications referenced by this paper.
Showing 1-10 of 21 references

Toward a model for lexical access based on acoustic landmarks and distinctive features

K. N. Stevens
The Journal of the Acoustical Society of America, vol. 111, no. 4, p. 1872, 2002. • 1872
View 5 Excerpts
Highly Influenced

Understanding how Deep Belief Networks perform acoustic modelling

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2012
View 4 Excerpts
Highly Influenced

New types of deep neural network learning for speech recognition and related applications: an overview

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013
View 3 Excerpts

Acoustic Modeling Using Deep Belief Networks

IEEE Transactions on Audio, Speech, and Language Processing • 2012
View 1 Excerpt

Boosting attribute and phone estimation accuracies with deep neural networks for detection-based speech recognition

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2012
View 1 Excerpt