Cited by 594Speech Recognition and SynthesisAdvanced Neural Network ApplicationsSpeech and Audio Processing

The DOI matches its Crossref record; 18 of the 21 references it cites were found in a registry or an index.

Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets

Sainath, Tara N., Kingsbury, Brian, Sindhwani, Vikas, Arisoy, Ebru, Ramabhadran, Bhuvana·2013·2013 IEEE International Conference on Acoustics, Speech and Signal Processing

DOI 10.1109/icassp.2013.6638949

Open this paper in CoChat — free account

Abstract

While Deep Neural Networks (DNNs) have achieved tremendous success for large vocabulary continuous speech recognition (LVCSR) tasks, training of these networks is slow. One reason is that DNNs are trained with a large number of training parameters (i.e., 10–50 million). Because networks are trained with a large number of output targets to achieve good performance, the majority of these parameters are in the final weight layer. In this paper, we propose a low-rank matrix factorization of the final weight layer. We apply this low-rank technique to DNNs for both acoustic modeling and language modeling. We show on three different LVCSR tasks ranging between 50–400 hrs, that a low-rank factorization reduces the number of parameters of the network by 30–50%. This results in roughly an equivalent reduction in training time, without a significant loss in final recognition accuracy, compared to a full-rank representation.

Integrity signals

Registry

Crossref · 10.1109/icassp.2013.6638949

Cites

18 of 18 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups
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
Self-citation
Convolutional networks for images, speech, and time series
LeCun, Y., & Bengio, Y. (1998) · HAL · doi:10.5555/303568.303704 · Cited by 4,646
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) · Cited by 1,839
Self-citation
Connectionist Speech Recognition: A Hybrid Approach
Bourlard, H. A., & Morgan, N. H. (1993) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 1,115
Deep convolutional neural networks for LVCSR
Sainath, T. N., Mohamed, A., Kingsbury, B. E. D., & Ramabhadran, B. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6639347 · Cited by 1,083
Self-citation
Conversational speech transcription using context-dependent deep neural networks
Seide, F. T. B., Li, G., & Yu, D. (2011) · Interspeech (USB) · doi:10.21437/interspeech.2011-169 · Cited by 877
Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription
Seide, F. T. B., Li, G., Xie, C., & Yu, D. (2011) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2011.6163899 · Cited by 648
Parallel stochastic gradient algorithms for large-scale matrix completion
Recht, B., & Ré, C. (2013) · Mathematical Programming Computation · doi:10.1007/s12532-013-0053-8 · Cited by 378
Introduction to Linear Algebra
DeFranza, J., & Gagliardi, D. (2008) · Cited by 378
Dimension Reduction and Coefficient Estimation in Multivariate Linear Regression
Yuan, M., Ekici, A., Lu, Z., & Monteiro, R. D. C. (2007) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/j.1467-9868.2007.00591.x · Cited by 310

Show all 21 references

Research works printed but not linked: 1

sainath, 2013, Exploring convolutional neural networks for large vo-cabulary speech recognition, Submitted to ICASSP

Sorted by citations

Items 301–400 of 594

Joint sparse neural network compression via multi-application multi-objective optimization
Chen, J., Xu, Y., Sun, W., & Huang, L. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02243-3 · Cited by 9
A Unified Federated DNNs Framework for Heterogeneous Mobile Devices
Li, X., Li, Y., Li, S., Zhou, Y., Chen, C., & Zheng, Z. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3088867 · Cited by 9
LC: A Flexible, Extensible Open-Source Toolkit for Model Compression
Idelbayev, Y., & Carreira-Perpiñán, M. Á. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482005 · Cited by 9
ComAI: Enabling Lightweight, Collaborative Intelligence by Retrofitting Vision DNNs
Jayarajah, K., Wanniarachchige, D., Abdelzaher, T., & Misra, A. (2022) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom48880.2022.9796769 · Cited by 9
ST-LoRA: Low-Rank Adaptation for Spatio-Temporal Forecasting
Ruan, W., Chen, W., Dang, X., Zhou, J., Li, W., Liu, X., & Liang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06109-6_20 · Cited by 16
Automated Quantization and Retraining for Neural Network Models Without Labeled Data
Thonglek, K., Takahashi, K., Ichikawa, K., Nakasan, C., Nakada, H., Takano, R., Leelaprute, P., & Iida, H. (2022) · IEEE Access · doi:10.1109/access.2022.3190627 · Cited by 8
A Design Space Exploration Methodology for Enabling Tensor Train Decomposition in Edge Devices
Kokhazadeh, M., Κεραμίδας, Γ., Kelefouras, V. I., & Stamoulis, I. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-15074-6_11 · Cited by 8
Unsupervised speaker adaptation of deep neural network based on the combination of speaker codes and singular value decomposition for speech recognition
Xue, S., Jiang, H., Dai, L.-R., & Liu, Q. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178833 · Cited by 8
Accelerating deep neural network filter pruning with mask-aware convolutional computations on modern CPUs
Ma, X., Li, G., Liu, L., Liu, H., & Wang, X. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.07.006 · Cited by 8
Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition
Lioutas, V., Rashid, A., Kumar, K., Haidar, M. A., & Rezagholizadeh, M. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.250 · Cited by 16
Hybrid Orthogonal Projection and Estimation (HOPE): A New Framework to Probe and Learn Neural NetworksPreprint
Zhang, S. S., & Jiang, H. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.00702 · Cited by 8
CacheNet: A Model Caching Framework for Deep Learning Inference on the EdgePreprint
Fang, Y., Shalmani, S. M., & Zheng, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.01793 · Cited by 8
GNN-RL Compression: Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning.Preprint
Yu, S., Mazaheri, A., & Jannesari, A. (2021) · arXiv (Cornell University) · Cited by 8
Mobile medical systems for equitable healthcare
Chan, J., Goel, M., Gollakota, S., & Nandakumar, R. (2025) · Nature Reviews Bioengineering · doi:10.1038/s44222-025-00330-5 · Cited by 8
A Construction Kit for Efficient Low Power Neural Network Accelerator Designs
Jokic, P., Azarkhish, E., Bonetti, A., Pons, M., Emery, S., & Benini, L. (2022) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3520127 · Cited by 9
Data-Driven Low-Rank Neural Network Compression
Papadimitriou, D., & Jain, S. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506467 · Cited by 9
A Practical Approach for Employing Tensor Train Decomposition in Edge Devices
Kokhazadeh, M., Κεραμίδας, Γ., Kelefouras, V. I., & Stamoulis, I. (2024) · International Journal of Parallel Programming · doi:10.1007/s10766-024-00762-3 · Cited by 7
Convolutional Neural Network Compression via Dynamic Parameter Rank Pruning
Sharma, M., Heard, J. R., Saber, E. S., & Markopoulos, P. P. (2025) · IEEE Access · doi:10.1109/access.2025.3533419 · Cited by 7
Neuron sparseness versus connection sparseness in deep neural network for large vocabulary speech recognition
Kang, J., Lu, C. Z., Cai, M., Zhang, W.-Q., & Liu, J. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178913 · Cited by 7
Parallel deep neural network training for LVCSR tasks using blue gene/Q
Sainath, T. N., Chung, I., Ramabhadran, B., Picheny, M., Gunnels, J. A., Kingsbury, B. E. D., Saon, G., Austel, V., & Chaudhari, U. V. (2014) · Interspeech (USB) · doi:10.21437/interspeech.2014-272 · Cited by 7
Self-citation
A comparison between deep neural nets and kernel acoustic models for speech recognition
Lu, Z., Quo, D., Garakani, A. B., Liu, K., May, A., Bellet, A., Fan, L., Collins, M., Kingsbury, B. E. D., Picheny, M., et al. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472643 · Cited by 7
Self-citation
SVD-based universal DNN modeling for multiple scenarios
Liu, C., Li, J., & Gong, Y. (2015) · Interspeech (USB) · doi:10.21437/interspeech.2015-658 · Cited by 7
On the Use of Acoustic Unit Discovery for Language Recognition
Shum, S. H., Harwath, D. F., Dehak, N., & Glass, J. R. (2016) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2016.2582260 · Cited by 7
Filter Sampling and Combination CNN (FSC-CNN): A Compact CNN Model for Small-footprint ASR Acoustic Modeling Using Raw Waveforms
Guo, J., Xu, N., Chen, X., Shi, Y., Xu, K., & Alwan, A. A. (2018) · Interspeech (USB) · doi:10.21437/interspeech.2018-1370 · Cited by 7
Dependable Deep Computation Model for Feature Learning on Big Data in Cyber-Physical Systems
Zhang, Q., Yang, L. T., Chen, Z., & Li, P. (2018) · ACM Transactions on Cyber-Physical Systems · doi:10.1145/3110218 · Cited by 7
Learning multimorbidity patterns from electronic health records using Non-negative Matrix Factorisation
Hassaïne, A., Canoy, D., Solares, J. R. A., Zhu, Y., Rao, S., Li, Y., Zottoli, M., Rahimi, K., & Salimi‐Khorshidi, G. (2020) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2020.103606 · Cited by 7
Embedding Compression with Isotropic Iterative Quantization
Liao, S., Chen, J., Wang, Y., Qiu, Q., & Yuan, B. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6350 · Cited by 7
Deep Neural Networks Regularization Using a Combination of Sparsity Inducing Feature Selection Methods
Farokhmanesh, F., & Sadeghi, M. T. (2021) · Neural Processing Letters · doi:10.1007/s11063-020-10389-3 · Cited by 7
Pruning for Compression of Visual Pattern Recognition Networks: A Survey from Deep Neural Networks Perspective
Bhalgaonkar, S., Munot, M. V., & Anuse, A. D. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-1520-8_55 · Cited by 7
Spatial Information Regularized Tensor Decomposition Framework for Super-Resolution Reconstruction of Medical MRI and Radiographs
Chen, X., Qiu, Y., Liang, W., Zhou, G., & Xie, S. (2022) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2022.3209099 · Cited by 7
Transport Object Detection in Street View Imagery Using Decomposed Convolutional Neural Networks
Bai, Y., Shang, C., Li, Y., Shen, L., Jin, S., & Shen, Q. (2023) · Mathematics · doi:10.3390/math11183839 · Cited by 8
Low-rank and sparse soft targets to learn better DNN acoustic models
Dighe, P., Asaei, A., & Bourlard, H. A. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7953161 · Cited by 7
Selecting optimal layer reduction factors for model reduction of deep neural networks
Mauch, L., & Yang, B. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952549 · Cited by 7
Studying the Effects of Feature Extraction Settings on the Accuracy and Memory Requirements of Neural Networks for Keyword Spotting
Shahnawaz, M., Plebani, E., Guaneri, I., Pau, D. P., & Marcon, M. (2018) · IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin) · doi:10.1109/icce-berlin.2018.8576243 · Cited by 7
Simplifying Deep Neural Networks for FPGA-Like Neuromorphic Systems
Chung, J., Shin, T., & Yang, J.-S. (2018) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2018.2877016 · Cited by 7
A flexible, extensible software framework for model compression based on the LC algorithmPreprint
Idelbayev, Y., & Carreira-Perpiñán, M. Á. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.07786 · Cited by 7
Rate-Distortion Theoretic Model Compression: Successive Refinement for PruningPreprint
Isik, B., No, A., & Weissman, T. (2021) · arXiv (Cornell University) · Cited by 7
Online Embedding Compression for Text Classification Using Low Rank Matrix Factorization
Acharya, A., Goel, R., Metallinou, A., & Dhillon, I. S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33016196 · Cited by 6
Parallel Neural Network Features for Improved Tandem Acoustic Modeling
Tüske, Z., Michel, W., Schlüter, R., & Ney, H. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-1747 · Cited by 6
AdaInNet: an adaptive inference engine for distributed deep neural networks offloading in IoT-FOG applications based on reinforcement learning
Etefaghi, A., & Sharifian, S. (2022) · The Journal of Supercomputing · doi:10.1007/s11227-022-04728-5 · Cited by 6
Nonmonotone variable projection algorithms for matrix decomposition with missing data
Su, X.-X., Gan, M., Chen, G., Yang, L., & Jin, J. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110150 · Cited by 6
Shell-Guided Compression of Voxel Radiance Fields
Yang, P., Ni, Z., Wang, H., Yang, W., Wang, S., & Kwong, S. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3538163 · Cited by 6
End-to-end speech recognition for languages with ideographic characters
Ito, H., Hagiwara, A., Ichiki, M., Mishima, T., Sato, S., & Kobayashi, A. (2017) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2017.8282226 · Cited by 6
Parameter Reduction For Deep Neural Network Based Acoustic Models Using Sparsity Regularized Factorization Neurons
Chung, H., Chung, E., Park, J. G., & Jung, H. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852021 · Cited by 6
Metric learning with rank and sparsity constraints
Bah, B., Becker, S., Cevher, V., & Gözcü, B. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6853550 · Cited by 6
Deep Learning in Speech Recognition
Iso, K.-I. (2017) · The Brain & Neural Networks · doi:10.3902/jnns.24.27 · Cited by 6
Analysis of Neural Network Based Language Modeling
Karuppusamy, P. (2020) · Journal of Artificial Intelligence and Capsule Networks · doi:10.36548/jaicn.2020.1.006 · Cited by 6
Fast LSTM by dynamic decomposition on cloud and distributed systems
You, Y., He, Y., Rajbhandari, S., Wang, W., Hsieh, C., Keutzer, K., & Demmel, J. W. (2020) · Knowledge and Information Systems · doi:10.1007/s10115-020-01487-8 · Cited by 6
Frivolous Units: Wider Networks Are Not Really That Wide
Casper, S., Boix, X., D’Amario, V., Guo, L., Schrimpf, M., Vinken, K., & Kreiman, G. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i8.16853 · Cited by 7
Memory Requirement Reduction of Deep Neural Networks for Field Programmable Gate Arrays Using Low-Bit Quantization of Parameters
Nicodemo, N., Naithani, G., Drossos, K., Virtanen, T. I., & Saletti, R. (2020) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco47968.2020.9287739 · Cited by 6
On the Redundancy in the Rank of Neural Network Parameters and Its Controllability
Lee, C., Kim, Y., Ji, H., Lee, Y., Hur, Y., & Lim, H. (2021) · Applied Sciences · doi:10.3390/app11020725 · Cited by 8
Reconstruction of Generative Adversarial Networks in Cross Modal Image Generation with Canonical Polyadic Decomposition
Ma, R., Lou, J., Li, P., & Gao, J. (2021) · Wireless Communications and Mobile Computing · doi:10.1155/2021/8868781 · Cited by 6
Factorized WaveNet for voice conversion with limited data
Du, H., Tian, X., Xie, L., & Li, H. (2021) · Speech Communication · doi:10.1016/j.specom.2021.03.003 · Cited by 6
Automated Customization of On-Device Inference for Quality-of-Experience Enhancement
Bai, Y., Chen, L., Ren, S., & Xu, J. (2022) · IEEE Transactions on Computers · doi:10.1109/tc.2022.3208207 · Cited by 6
Towards implicit complexity control using variable-depth deep neural networks for automatic speech recognition
Tan, S., & Sim, K. C. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472822 · Cited by 6
Compression of Acoustic Model via Knowledge Distillation and Pruning
Li, C., Zhu, L., Xu, S., Gao, P., & Xu, B. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545028 · Cited by 6
Sparse Linear Networks with a Fixed Butterfly Structure: Theory and PracticePreprint
Ailon, N., Leibovich, O., & Nair, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08864 · Cited by 8
An Accuracy-Preserving Neural Network Compression via Tucker Decomposition
Liu, C., Xie, K., Wen, J., Xie, G., & Li, K. (2024) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2024.3425962 · Cited by 6
HpT: Hybrid Acceleration of Spatio-Temporal Attention Model Training on Heterogeneous Manycore Architectures
Dahal, S., Dhingra, P., Thapa, K. K., Pande, P. P., & Kalyanaraman, A. (2025) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2024.3522781 · Cited by 7
Deepsub: A Novel Subset Selection Framework for Training Deep Learning Architectures
Banerjee, S., & Chakraborty, S. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803096 · Cited by 6
Text-to-Speech with Model Compression on Edge Devices
Koc, W.-W., Chang, Y., Yu, J.-Y., & İk, T.-U. (2021) · Asia-Pacific Network Operations and Management Symposium (APNOMS) · doi:10.23919/apnoms52696.2021.9562651 · Cited by 5
Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions
Heymann, J., Haeb‐Umbach, R., Golik, P., & Schlüter, R. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178933 · Cited by 5
Low-Rank Representation of Nearest Neighbor Posterior Probabilities to Enhance DNN Based Acoustic Modeling
Luyet, G., Dighe, P., Asaei, A., & Bourlard, H. A. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-1279 · Cited by 5
Entropy-based pruning of hidden units to reduce DNN parameters
Mantena, G., & Sim, K. C. (2016) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2016.7846335 · Cited by 5
Bandwidth Embeddings for Mixed-Bandwidth Speech Recognition
Mantena, G., Kalinli, O., Abdel‐Hamid, O., & McAllaster, D. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-2589 · Cited by 5
Automatic Selection of Tensor Decomposition for Compressing Convolutional Neural Networks A Case Study on VGG-type Networks
Liang, C., & Lee, C. (2021) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw52791.2021.00115 · Cited by 5
Supervised Hashing with Deep Neural NetworksPreprint
Zhang, Z., Chen, Y., & Saligrama, V. (2015) · arXiv (Cornell University) · Cited by 5
DEEPEYE: A Compact and Accurate Video Comprehension at Terminal Devices Compressed with Quantization and TensorizationPreprint
Cheng, Y., Li, G., Chen, H., Tan, S. X.-D., & Yu, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.07935 · Cited by 5
ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models
Yuan, Z., Shang, Y., Song, Y., Yang, D., Wu, Q., Yan, Y., & Sun, G. (2023) · arXiv · doi:10.48550/arxiv.2312.05821 · Cited by 4
“…methods typically involve decomposing weight matrices of pre-trained networks using techniques like Singular Value Decomposition (SVD) or tensor decomposition, followed by fine-tuning the factorized network [Denton et al., 2014, Lebedev et al., 2014, Sainath et al., 2013, Moczulski et al., 2015].”
BackgroundMethod
Tiny Federated Wireless Foundation Models for Resource-Constrained Devices
Hallaq, M., Khan, F. M. A., Aboulfotouh, A., Hassan, S. A., Dev, K., Quasim, M. T., & Abou-Zeid, H. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3591169 · Cited by 4
TEC-CNN: Toward Efficient Compressing of Convolutional Neural Nets with Low-rank Tensor Decomposition
Wang, Y., Feng, L., Cai, F., Li, L., Wu, R., & Li, J. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3702641 · Cited by 4
Sequence training and adaptation of highway deep neural networks
Lu, L. (2016) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2016.7846304 · Cited by 4
Hybrid Kronecker Product Decomposition and Approximation
Cai, C., Chen, R., & Han, X. G. (2022) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2022.2134873 · Cited by 4
Multi‐scale contextual learning for medical image segmentation via dual distillation
Cui, R., Liu, L., Song, Y., Ren, G., Hu, X., & Qin, J. (2024) · Medical Physics · doi:10.1002/mp.17506 · Cited by 4
Exemplar-based large vocabulary speech recognition using k-nearest neighbors
Xu, Y., Siohan, O., Simcha, D., Kumar, S., & Liao, H. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178956 · Cited by 4
Recurrent Neural Networks and Related Models
Yu, D., & Deng, L. (2014) · Signals and communication technology · doi:10.1007/978-1-4471-5779-3_13 · Cited by 5
Improvements in RWTH LVCSR evaluation systems for Polish, Portuguese, English, urdu, and Arabic
Shaik, M. A. B., Tüske, Z., Tahir, M. A., Nußbaum-Thom, M., Schlüter, R., & Ney, H. (2015) · Interspeech (USB) · doi:10.21437/interspeech.2015-635 · Cited by 4
Deep Discriminative and Generative Models for Pattern Recognition
Deng, L., & Jaitly, N. (2015) · Cited by 4
Student-Teacher Training with Diverse Decision Tree Ensembles
Wong, J. H. M., & Gales, M. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-145 · Cited by 4
Accelerating deep neural network learning for speech recognition on a cluster of GPUs
Cong, G., Kingsbury, B. E. D., Gosh, S., Saon, G., & Zhou, F. (2017) · doi:10.1145/3146347.3146351 · Cited by 4
Self-citation
Scalable Learning to Optimize: A Learned Optimizer Can Train Big Models
Chen, X., Chen, T., Cheng, Y., Chen, W., Awadallah, A. H., & Wang, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20050-2_23 · Cited by 5
Mask-Net: A Hardware-efficient Object Detection Network with Masked Region Proposals
Chen, H., & Hao, C. (2022) · IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) · doi:10.1109/asap54787.2022.00030 · Cited by 5
Structured Bayesian Federated Learning for Green AI: A Decentralized Model Compression Using Turbo-VBI-Based Approach
Xia, C., Tsang, D. H. K., & Lau, V. K. N. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3335971 · Cited by 4
Comparative Evaluation between Accelerated RISC- V and ARM AI Inference Machines
Christofas, V., Amanatidis, P., Karampatzakis, D., Λάγκας, Θ., Goudos, S. K., Psannis, K. E., & Sarigiannidis, P. G. (2023) · World Symposium on Communication Engineering (WSCE) · doi:10.1109/wsce59557.2023.10365853 · Cited by 4
Robustness of Compressed Convolutional Neural Networks
Wijayanto, A. W., Jin, C. J., Madhawa, K., & Murata, T. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622371 · Cited by 4
Fast Training of Deep Neural Networks for Speech Recognition
Cong, G., Kingsbury, B. E. D., Yang, C.-C., & Liu, T. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053993 · Cited by 4
Self-citation
Knowledge Distillation via Channel Correlation Structure
Li, B., Chen, B., Wang, Y., Dai, T., Hu, M., Jiang, Y., & Xia, S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-82136-4_29 · Cited by 4
Speeding up Deep Neural Networks in Speech Recognition with Piecewise Quantized Sigmoidal Activation Function
Anhao, X., Zhao, Q., & Yan, Y. (2016) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2016sll0007 · Cited by 4
Acoustic model training based on node-wise weight boundary model for fast and small-footprint deep neural networks
Takeda, R., Nakadai, K., & Komatani, K. (2017) · Computer Speech & Language · doi:10.1016/j.csl.2017.02.002 · Cited by 4
Cross Domain Model Compression by Structurally Weight Sharing
Gao, S., Deng, C. D., & Huang, H. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00918 · Cited by 4
DenseNet-DC: Optimizing DenseNet Parameters Through Feature Map Generation Control
da Silva, A. T., & SIEBERT, C. R. (2020) · Revista de Informática Teórica e Aplicada · doi:10.22456/2175-2745.98369 · Cited by 3
Simplifying Neural Networks via Look up Tables and Product of Sums Matrix Factorizations
Wu, C. W. (2020) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas45731.2020.9180985 · Cited by 4
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
Chen, X., Chen, T., Chen, W., Awadallah, A. H., Wang, Z., & Cheng, Y. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.456 · Cited by 15
C3-Flow
Sotoudeh, M., & Baghsorkhi, S. S. (2019) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3316781.3317786 · Cited by 4
Refining Architectures of Deep Convolutional Neural NetworksPreprint
Shankar, S., Robertson, D., Ioannou, Y., Criminisi, A., & Cipolla, R. (2016) · arXiv (Cornell University) · doi:10.17863/cam.13046 · Cited by 4
Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNNPreprint
Ding, X., Hao, T., Han, J., Guo, Y., & Ding, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.14444 · Cited by 4
Compact representations of convolutional neural networks via weight pruning and quantizationPreprint
Marinò, G. C., Petrini, A., Malchiodi, D., & Frasca, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.12704 · Cited by 4
A Multimodal Large Language Model for Forestry in pest and disease recognitionPreprint
Zhang, M., Li, X., Du, Y., Rao, Z., Chen, S., Wang, W., Chen, X., Huang, D., & Wang, S. (2023) · Research Square · doi:10.21203/rs.3.rs-3444472/v1 · Cited by 5
A Comprehensive Survey on Recent Model Compression and Acceleration Approaches for Deep Neural Networks and TransformersPreprint
XU, G., Huang, W., & Jia, W. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4893335 · Cited by 5
Model Compression for Sustainable AI in xG Wireless Networks: Recent Advances, Challenges, and Future Directions
Khan, F. M. A., Hallaq, M., Abou-Zeid, H., Erak, O., Waqar, O., Hassan, S. A., Alhussein, O., & Hossain, E. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3682638 · Cited by 3

Authors: Sainath, T. N., Kingsbury, B., Sindhwani, V., Arisoy, E., & Ramabhadran, B.
Affiliations: IBM (United States) (US)
ORCID: Sainath, Tara N.
Kingsbury, Brian
Ramabhadran, Bhuvana
Venue: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
Publisher: IEEE
Published: 2013-05
Pages: 6655-6659
ISSN: 1520-6149 (ISSN-L)
DOI: 10.1109/icassp.2013.6638949
OpenAlex: W2058641082
Cited by: 593
References: 21
Citations by year: 2026: 17 · 2025: 38 · 2024: 36 · 2023: 40 · 2022: 53 · 2021: 64 · 2020: 71 · 2019: 52 · 2018: 54 · 2017: 48 · 2016: 55 · 2015: 37 · 2014: 24 · 2013: 4
FWCI: 25.84
Type: conference paper
Language: en
Open access: closed
Locations: IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
Topics: Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
Keywords: low-rank factorization, deep neural network training, large vocabulary continuous speech recognition, parameter reduction, acoustic modeling, language modeling, training time reduction

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

Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Citations

Cites

Cited by

Related

Metadata

Record

About these checks