Noisy training for deep neural networks in speech recognition
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Deep neural networks (DNNs) have gained remarkable success in speech recognition, partially attributed to the flexibility of DNN models in learning complex patterns of speech signals. This flexibility, however, may lead to serious over-fitting and hence miserable performance degradation in adverse acoustic conditions such as those with high ambient noises. We propose a noisy training approach to tackle this problem: by injecting moderate noises into the training data intentionally and randomly, more generalizable DNN models can be learned. This ‘noise injection’ technique, although known to the neural computation community already, has not been studied with DNNs which involve a highly complex objective function. The experiments presented in this paper confirm that the noisy training approach works well for the DNN model and can provide substantial performance improvement for DNN-based speech recognition.
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
Extracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436
Deep Learning: Methods and Applications
Deng, L., & Yu, D. (2014) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000039 · Cited by 3,480 · cited 3×
“The advantage of DNNs in modeling state emission distributions, when compared to the conventional GMM, has been discussed in some previous publications, e.g., [1,2].”
BackgroundContext-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 1×
“the new model is predominantly superior to the classical architecture based on GMMs [2,4,6-13].”
MethodTraining with Noise is Equivalent to Tikhonov Regularization
Bishop, C. M. (1995) · Neural Computation · doi:10.1162/neco.1995.7.1.108 · Cited by 1,325
The Effects of Adding Noise During Backpropagation Training on a Generalization Performance
An, G. (1996) · Neural Computation · doi:10.1162/neco.1996.8.3.643 · Cited by 475 · cited 2×
“The noisy training approach proposed in this paper was highly motivated by the noise injection theory which has been known for decades in the neural computing community [31-34].”
BackgroundMethodNoise Injection: Theoretical Prospects
Grandvalet, Y., Canu, S., & Boucheron, S. (1997) · Neural Computation · doi:10.1162/neco.1997.9.5.1093 · Cited by 147 · cited 1×
“The noisy training approach proposed in this paper was highly motivated by the noise injection theory which has been known for decades in the neural computing community [31-34].”
Method
Cited by
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
Convolutional Neural Networks: A Survey
Krichen, M. (2023) · Computers · doi:10.3390/computers12080151 · Cited by 623
“Convolutional neural networks (CNNs) [14–16] are a popular type of ML model that have been widely utilized for various tasks, including image recognition [17–20], speech recognition [21–25], and NLP [26–30].”
An Unsupervised-Learning-Based Approach for Automated Defect Inspection on Textured Surfaces
Mei, S., Yang, H., & Yin, Z. (2018) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2795178 · Cited by 308
“It should not be used in the testing phase so as to ensure fairness of performance comparison [35].”
BackgroundMethodInfluentialChristensen, J. H., Whiston, H., Lough, M., Gil-Carvajal, J. C., Rumley, J., & Saunders, G. H. (2024) · American Journal of Audiology · doi:10.1044/2023_aja-23-00149 · Cited by 19
Metadata
- Authors
- Yin, S., Liu, C., Zhang, Z., Lin, Y., Wang, D., Tejedor, J., Zheng, T. F., & Li, Y.
- Venue
- EURASIP Journal on Audio, Speech, and Music Processing
- Published
- 2015-01-20
- Volume
- 2015
- Issue
- 1
- ISSN
- 1687-4714 (ISSN-L)
- 1687-4722
- OpenAlex
- W2096653978
- Cited by
- 118
- References
- 6
- FWCI
- 9.38
- Type
- journal article
- Language
- en
- Open access
- gold
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: Noisy training for deep neural networks in speech recognition. https://app.cochat.ai/papers/10.1186/s13636-014-0047-0
- The paper
- Yin, S., Liu, C., Zhang, Z., Lin, Y., Wang, D., Tejedor, J., Zheng, T. F., & Li, Y. (2015). Noisy training for deep neural networks in speech recognition. EURASIP Journal on Audio, Speech, and Music Processing. https://doi.org/10.1186/s13636-014-0047-0
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.