Phone recognition with hierarchical convolutional deep maxout networks
@article{Tth2015PhoneRW, title={Phone recognition with hierarchical convolutional deep maxout networks}, author={L. T{\'o}th}, journal={EURASIP Journal on Audio, Speech, and Music Processing}, year={2015}, volume={2015}, pages={1-13} }
Deep convolutional neural networks (CNNs) have recently been shown to outperform fully connected deep neural networks (DNNs) both on low-resource and on large-scale speech tasks. Experiments indicate that convolutional networks can attain a 10–15 % relative improvement in the word error rate of large vocabulary recognition tasks over fully connected deep networks. Here, we explore some refinements to CNNs that have not been pursued by other authors. First, the CNN papers published up till now… CONTINUE READING
Figures, Tables, and Topics from this paper
77 Citations
A Hybrid of Deep CNN and Bidirectional LSTM for Automatic Speech Recognition
- Computer Science
- J. Intell. Syst.
- 2020
- 7
- PDF
An analysis of convolutional neural networks for speech recognition
- Computer Science
- 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2015
- 80
- PDF
Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks
- Computer Science, Mathematics
- INTERSPEECH
- 2016
- 244
- PDF
Deep neural networks with linearly augmented rectifier layers for speech recognition
- Computer Science
- 2018 IEEE 16th World Symposium on Applied Machine Intelligence and Informatics (SAMI)
- 2018
A comparative analysis of pooling strategies for convolutional neural network based Hindi ASR
- Computer Science
- J. Ambient Intell. Humaniz. Comput.
- 2020
- 3
Evaluation of maxout activations in deep learning across several big data domains
- Computer Science
- Journal of Big Data
- 2019
- 8
Multi-level region-of-interest CNNs for end to end speech recognition
- Computer Science
- J. Ambient Intell. Humaniz. Comput.
- 2019
- 7
References
SHOWING 1-10 OF 69 REFERENCES
Exploring convolutional neural network structures and optimization techniques for speech recognition
- Computer Science
- INTERSPEECH
- 2013
- 298
- PDF
Deep Convolutional Neural Networks for Large-scale Speech Tasks
- Computer Science, Medicine
- Neural Networks
- 2015
- 326
Deep convolutional neural networks for LVCSR
- Computer Science
- 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
- 2013
- 847
- PDF
Improvements to Deep Convolutional Neural Networks for LVCSR
- Computer Science, Mathematics
- 2013 IEEE Workshop on Automatic Speech Recognition and Understanding
- 2013
- 169
- PDF
An analysis of convolutional neural networks for speech recognition
- Computer Science
- 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2015
- 80
- PDF
Deep maxout neural networks for speech recognition
- Computer Science
- 2013 IEEE Workshop on Automatic Speech Recognition and Understanding
- 2013
- 58
Improving deep neural networks for LVCSR using rectified linear units and dropout
- Computer Science
- 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
- 2013
- 983
- PDF
Convolutional maxout neural networks for low-resource speech recognition
- Computer Science
- The 9th International Symposium on Chinese Spoken Language Processing
- 2014
- 14
Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition
- Computer Science
- 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2012
- 714
- PDF