Extracting deep bottleneck features using stacked auto-encoders
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
In this work, a novel training scheme for generating bottleneck features from deep neural networks is proposed. A stack of denoising auto-encoders is first trained in a layer-wise, unsupervised manner. Afterwards, the bottleneck layer and an additional layer are added and the whole network is fine-tuned to predict target phoneme states. We perform experiments on a Cantonese conversational telephone speech corpus and find that increasing the number of auto-encoders in the network produces more useful features, but requires pre-training, especially when little training data is available. Using more unlabeled data for pre-training only yields additional gains. Evaluations on larger datasets and on different system setups demonstrate the general applicability of our approach. In terms of word error rate, relative improvements of 9.2% (Cantonese, ML training), 9.3% (Tagalog, BMMI-SAT training), 12% (Tagalog, confusion network combinations with MFCCs), and 8.7% (Switchboard) are achieved.
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 fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336
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
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
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×
“used a deep belief network (DBN) where each layer is modeled by a restricted Boltzmann machine (RBM), later works showed that other architectures like auto-encoders [5] or convolutional neural networks [6] are suitable for building deep networks using similar schemes as well.”
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 · cited 1×
“Recently, deep neural networks have been used with great success in hybrid DNN/HMM systems, resulting in strong improvements on challenging large-vocabulary tasks such as Switchboard [10] or Bing voice search data [11].”
MethodPhoneme recognition using time-delay neural networks
Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., & Lang, K. J. (1989) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/29.21701 · Cited by 2,643
Self-citationSWITCHBOARD: telephone speech corpus for research and development
Godfrey, J. J., Holliman, E. C., & McDaniel, J. (1992) · [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1992.225858 · Cited by 2,134
Deep Neural Networks for Acoustic Modeling in Speech Recognition
Hinton, G. E., Deng, L., Yu, D., Dahl, G. E., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T. N., et al. (2012) · IEEE Signal Processing Magazine · Cited by 2,114
Connectionist Speech Recognition: A Hybrid Approach
Bourlard, H. A., & Morgan, N. H. (1993) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 1,115
Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition
Ranzato, M., Huang, F. J., Boureau, Y.-L., & LeCun, Y. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383157 · Cited by 1,086
Theano: A CPU and GPU Math Compiler in Python
Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., & Bengio, Y. (2010) · Proceedings of the Python in Science Conference · doi:10.25080/majora-92bf1922-003 · Cited by 1,052
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
Tandem connectionist feature extraction for conventional HMM systems
Hermansky, H., Ellis, D. P. W., & Sharma, S. (2002) · 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100) · doi:10.1109/icassp.2000.862024 · Cited by 693
Connectionist Speech Recognition
Bourlard, H. A., & Morgan, N. (1994) · Springer eBooks · doi:10.1007/978-1-4615-3210-1 · Cited by 585
Review of Neural Networks for Speech Recognition
Lippmann, R. P. (1989) · Neural Computation · doi:10.1162/neco.1989.1.1.1 · Cited by 477
Improved bottleneck features using pretrained deep neural networks
Yu, D., & Seltzer, M. L. (2011) · Interspeech 2011 · doi:10.21437/interspeech.2011-91 · Cited by 272
Understanding how Deep Belief Networks perform acoustic modelling
Mohamed, A.-R., Hinton, G., & Penn, G. (2012) · 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2012.6288863 · Cited by 265
Auto-encoder bottleneck features using deep belief networks
Sainath, T. N., Kingsbury, B., & Ramabhadran, B. (2012) · 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2012.6288833 · Cited by 182
Optimizing 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
Conversational speech transcription using context-dependent deep neural networks
Yu, D., Seide, F. T. B., & Li, G. (2012) · International Conference on Machine Learning · Cited by 131
The IBM 2011 GALE Arabic speech transcription system
Mangu, L., Kuo, H.-K. J., Chu, S. M., Kingsbury, B. E. D., Saon, G., Soltau, H., & Biadsy, F. (2011) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2011.6163943 · Cited by 30
Cited by
A survey on deep learning for big data
Zhang, Q., Yang, L. T., Chen, Z., & Li, P. (2018) · Information Fusion · doi:10.1016/j.inffus.2017.10.006 · Cited by 1,226
Mobile sensor data anonymization
Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H. (2019) · Proceedings of the International Conference on Internet of Things Design and Implementation · doi:10.1145/3302505.3310068 · Cited by 298
“The information bottleneck [4, 10] in the middle layer of the CAE helps the encoding part of the CAE to capture the main factors of variation in the data into this latent representation.”
BackgroundDeep learning methods in transportation domain: a review
Nguyen, H., Kieu, L., Wen, T., & Cai, C. (2018) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2018.0064 · Cited by 285
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
- Gehring, J., Miao, Y., Metze, F., & Waibel, A.
- Venue
- 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
- Publisher
- IEEE
- Published
- 2013-05
- Pages
- 3377-3381
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W1970088388
- Cited by
- 274
- References
- 21
- FWCI
- 17.35
- Type
- conference paper
- Language
- en
- Open access
- green
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.