Optimization Techniques to Improve Training Speed of Deep Neural Networks for Large Speech Tasks
The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
While Deep Neural Networks (DNNs) have achieved tremendous success for large vocabulary continuous speech recognition (LVCSR) tasks, training these networks is slow. Even to date, the most common approach to train DNNs is via stochastic gradient descent, serially on one machine. Serial training, coupled with the large number of training parameters (i.e., 10-50 million) and speech data set sizes (i.e., 20-100 million training points) makes DNN training very slow for LVCSR tasks. In this work, we explore a variety of different optimization techniques to improve DNN training speed. This includes parallelization of the gradient computation during cross-entropy and sequence training, as well as reducing the number of parameters in the network using a low-rank matrix factorization. Applying the proposed optimization techniques, we show that DNN training can be sped up by a factor of 3 on a 50-hour English Broadcast News (BN) task with no loss in accuracy. Furthermore, using the proposed techniques, we are able to train DNNs on a 300-hr Switchboard (SWB) task and a 400-hr English BN task, showing improvements between 9-30% relative over a state-of-the art GMM/HMM system while the number of parameters of the DNN is smaller than the GMM/HMM system.
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
A Practical Guide to Training Restricted Boltzmann Machines
Hinton, G. E. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_32 · Cited by 2,852
Large-scale deep unsupervised learning using graphics processors
Raina, R., Madhavan, A., & Ng, A. Y. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553486 · Cited by 742
Cited by
Deep Learning: Methods and Applications
Deng, L., & Yu, D. (2014) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000039 · Cited by 3,480
“The success was quickly extended to large vocabulary speech recognition tasks with hundreds and even thousands of hours of training set and with thousands of tri-phone states, including the Switchboard and Broadcast News databases, and Google’s voice search and YouTube tasks [94, 161, 184, 309, 311, 324].”
BackgroundInfluentialDeep Learning: Methods and Applications
Deng, L. (2014) · now publishers, Inc. eBooks · doi:10.1561/9781601988157 · Cited by 1,759
An Overview of Noise-Robust Automatic Speech Recognition
Li, J., Deng, L., Gong, Y., & Haeb-Umbach, R. (2014) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2014.2304637 · Cited by 568
Seide, F., Fu, H., Droppo, J., Li, G., & Yu, D. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-274 · Cited by 443
Fundamentals of speech recognition
Li, J., Deng, L., Haeb-Umbach, R., & Gong, Y. (2016) · Robust Automatic Speech Recognition · doi:10.1016/b978-0-12-802398-3.00002-7 · Cited by 266
Metadata
- Authors
- Sainath, T. N., Kingsbury, B., Soltau, H., & Ramabhadran, B.
- Venue
- IEEE Transactions on Audio, Speech, and Language Processing
- Published
- 2013-11
- Volume
- 21
- Issue
- 11
- Pages
- 2267-2276
- ISSN
- 1558-7916 (ISSN-L)
- 1558-7924
- OpenAlex
- W2071310251
- Cited by
- 59
- References
- 2
- FWCI
- 11.04
- Type
- journal article
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Optimization Techniques to Improve Training Speed of Deep Neural Networks for Large Speech Tasks. https://app.cochat.ai/papers/10.1109/tasl.2013.2284378
- The paper
- Sainath, T. N., Kingsbury, B., Soltau, H., & Ramabhadran, B. (2013). Optimization Techniques to Improve Training Speed of Deep Neural Networks for Large Speech Tasks. IEEE Transactions on Audio, Speech, and Language Processing. https://doi.org/10.1109/tasl.2013.2284378
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.