The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Improved bottleneck features using pretrained deep neural networks
Abstract
Bottleneck features have been shown to be effective in improving the accuracy of automatic speech recognition (ASR) systems. Conventionally, bottleneck features are extracted from a multi-layer perceptron (MLP) trained to predict context-independent monophone states. The MLP typically has three hidden layers and is trained using the backpropagation algorithm. In this paper, we propose two improvements to the training of bottleneck features motivated by recent advances in the use of deep neural networks (DNNs) for speech recognition. First, we show how the use of unsupervised pretraining of a DNN enhances the network’s discriminative power and improves the bottleneck features it generates. Second, we show that a neural network trained to predict context-dependent senone targets produces better bottleneck features than one trained to predict monophone states. Bottleneck features trained using the proposed methods produced a 16% relative reduction in sentence error rate over conventional bottleneck features on a large vocabulary business search task.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 1×
“Because 〈(cid:22) (cid:17) ℎ (cid:18) 〉 03*45 is extremely expensive to compute exactly, the contrastive divergence (CD) approximation to the gradient is used, where 〈(cid:22) (cid:17) ℎ (cid:18) 〉 03*45 is replaced by running the Gibbs sampler initialized at the data for one full step [12].”
MethodContext-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
Self-citationAcoustic Modeling Using Deep Belief Networks
Mohamed, A.-R., Dahl, G. E., & Hinton, G. (2012) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2011.2109382 · Cited by 1,727
Probabilistic and Bottle-Neck Features for LVCSR of Meetings
Grezl, F., Karafiat, M., Kontar, S., & Cernocky, J. (2007) · 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 · doi:10.1109/icassp.2007.367023 · Cited by 340
Investigation of full-sequence training of deep belief networks for speech recognition
Mohamed, A.-R., Yu, D., & Deng, L. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-304 · Cited by 210
Self-citationYu, D., Deng, L., & Dahl, G. E. (2010) · neural information processing systems · Cited by 189
Self-citationOptimizing bottle-neck features for lvcsr
Grézl, F., & Fousek, P. (2008) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2008.4518713 · Cited by 132
TRAPS - classifiers of temporal patterns
Heřmanský, H., & Sharma, S. (1998) · International Conference on Spoken Language Processing (ICSLP) · doi:10.21437/icslp.1998-524 · Cited by 125
Live search for mobile:Web services by voice on the cellphone
Acero, A., Bernstein, N., Chambers, R., Ju, Y.-C., Li, X., Odell, J. J., Nguyen, P., Scholz, O., & Zweig, G. (2008) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2008.4518845 · Cited by 68
Cited by
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
Unsupervised speech representation learning using WaveNet autoencoders
Chorowski, J., Weiss, R. J., Bengio, S., & van den Oord, A. (2019) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2019.2938863 · Cited by 325
Extracting deep bottleneck features using stacked auto-encoders
Gehring, J., Miao, Y., Metze, F., & Waibel, A. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638284 · Cited by 274
Caffeine: Toward Uniformed Representation and Acceleration for Deep Convolutional Neural Networks
Zhang, C., Sun, G., Fang, Z., Zhou, P., Pan, P., & Cong, J. (2019) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2017.2785257 · Cited by 270
Metadata
- Authors
- Yu, D., & Seltzer, M. L.
- Venue
- Interspeech 2011
- Publisher
- ISCA
- Published
- 2011-08-27
- Pages
- 237-240
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2123237149
- Cited by
- 272
- References
- 11
- FWCI
- 14.57
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Improved bottleneck features using pretrained deep neural networks. https://app.cochat.ai/papers/10.21437/interspeech.2011-91
- The paper
- Yu, D., & Seltzer, M. L. (2011). Improved bottleneck features using pretrained deep neural networks. Interspeech 2011. https://doi.org/10.21437/interspeech.2011-91
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.