Improving deep neural network acoustic models using generalized maxout networks
The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Recently, maxout networks have brought significant improvements to various speech recognition and computer vision tasks. In this paper we introduce two new types of generalized maxout units, which we call p-norm and soft-maxout. We investigate their performance in Large Vocabulary Continuous Speech Recognition (LVCSR) tasks in various languages with 10 hours and 60 hours of data, and find that the p-norm generalization of maxout consistently performs well. Because, in our training setup, we sometimes see instability during training when training unbounded-output nonlinearities such as these, we also present a method to control that instability. This is the “normalization layer”, which is a nonlinearity that scales down all dimensions of its input in order to stop the average squared output from exceeding one. The performance of our proposed nonlinearities are compared with maxout, rectified linear units (ReLU), tanh units, and also with a discriminatively trained SGMM/HMM system, and our p-norm units with p equal to 2 are found to perform best.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260
(2011) · Cited by 6,993
Improving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382
Greedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841 · cited 1×
“Instead we do something similar to the greedy layer-wise supervised training [19] or the “layer-wise backpropagation” of [3].”
MethodKaldi Speech Recognition Toolkit
Povey, D. (2024) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.57702/jb3fvbn9 · Cited by 4,609
Self-citationLarge Scale Distributed Deep Networks
Dean, J. B., Corrado, G. S., Monga, R., Chen, K., Devin, M., Mao, M., Ranzato, M., Senior, A., Tucker, P. A., Yang, K., et al. (2012) · neural information processing systems · Cited by 4,489
Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition
Dahl, G. E., Yu, D., Deng, L., & Acero, A. (2012) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2134090 · Cited by 3,011 · cited 2×
“Following the recent success of pre-trained deep neural networks based on sigmoidal units [1, 2, 3] and the popularity of “deep learning”, a number of different nonlinearities (activation functions) have been proposed for neural network training.”
BackgroundMethodA Theoretical Analysis of Feature Pooling in Visual Recognition
Boureau, Y.-L., Ponce, J., & LeCun, Y. (2010) · Cited by 1,661
Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
Niu, F., Recht, B., Re, C., & Wright, S. J. (2011) · arXiv · doi:10.48550/arxiv.1106.5730 · Cited by 1,211
Conversational speech transcription using context-dependent deep neural networks
Seide, F., Li, G., & Yu, D. (2011) · Interspeech 2011 · doi:10.21437/interspeech.2011-169 · Cited by 852
Cited by
“Librispeech: an ASR corpus based on public domain audio books,”
Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178964 · Cited by 6,072
Self-citationEfficient Processing of Deep Neural Networks: A Tutorial and Survey
Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2017.2761740 · Cited by 4,215
“Finally, a non-linearity called maxout, which takes the max value of two intersecting linear functions, has shown to be effective in speech recognition tasks [44, 45].”
Deep Learning: Methods and Applications
Deng, L., & Yu, D. (2014) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000039 · Cited by 3,480
Deep Learning: Methods and Applications
Deng, L. (2014) · now publishers, Inc. eBooks · doi:10.1561/9781601988157 · Cited by 1,759
Speech Recognition Using Deep Neural Networks: A Systematic Review
Nassif, A. B., Shahin, I., Attili, I., Azzeh, M., & Shaalan, K. (2019) · IEEE Access · doi:10.1109/access.2019.2896880 · Cited by 1,152
Audio augmentation for speech recognition
Ko, T., Peddinti, V., Povey, D., & Khudanpur, S. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-711 · Cited by 1,104
Self-citationA time delay neural network architecture for efficient modeling of long temporal contexts
Peddinti, V., Povey, D., & Khudanpur, S. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-647 · Cited by 986
“p-norm units with group size of 10 and p = 2 were used across all neural networks in our experiments, based on the observations made in [15] (1).”
BackgroundMethodSelf-citationSeide, F., Fu, H., Droppo, J., Li, G., & Yu, D. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-274 · Cited by 443
Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
Hershey, J. R., Roux, J. L., & Weninger, F. (2014) · arXiv · doi:10.48550/arxiv.1409.2574 · Cited by 412
“…and (23), neglecting the schedule, and considering the reciprocal messages m k − 1 i j ( h j ) to be uniform, leads to the updates, This appears comparable to two commonly used forms: (29) is similar in spirit to softmaxout [25], and the max-product version (30) is similar in spirit to maxout [24].”
MethodTowards End-to-End Speech Recognition with Deep Convolutional Neural Networks
Zhang, Y., Pezeshki, M., Brakel, P., Zhang, S., Laurent, C., Bengio, Y., & Courville, A. (2016) · Interspeech 2016 · doi:10.21437/interspeech.2016-1446 · Cited by 352
Li, X., & Wu, X. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178826 · Cited by 336
Parallel training of DNNs with Natural Gradient and Parameter Averaging
Povey, D., Zhang, X., & Khudanpur, S. (2014) · arXiv · doi:10.48550/arxiv.1410.7455 · Cited by 148
Self-citation
Metadata
- Authors
- Zhang, X., Trmal, J., Povey, D., & Khudanpur, S.
- Venue
- 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2014-05
- Pages
- 215-219
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2026369565
- Cited by
- 273
- References
- 26
- FWCI
- 27.67
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.