EXTRACTING DEEP NEURAL NETWORK BOTTLENECK FEATURES USING LOW-RANK MATRIX FACTORIZATION

被引：0

作者：

Zhang, Yu ^{[1
]}

Chuangsuwanich, Ekapol ^{[1
]}

Glass, James ^{[1
]}

机构：

[1] MIT, Comp Sci & Artificial Intelligence Lab, Cambridge, MA 02139 USA

来源：

2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2014年

关键词：

DNN; Bottleneck features;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

In this paper, we investigate the use of deep neural networks (DNNs) to generate a stacked bottleneck (SBN) feature representation for low-resource speech recognition. We examine different SBN extraction architectures, and incorporate low-rank matrix factorization in the final weight layer. Experiments on several low-resource languages demonstrate the effectiveness of the SBN configurations when compared to state-of-the-art hybrid DNN approaches.

引用

页数：5

共 50 条

[41] Accelerated Factored Gradient Descent for Low-Rank Matrix Factorization
Zhou, Dongruo
Cao, Yuan
Gu, Quanquan
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108 : 4430 - 4439
[42] Low-Rank Matrix Factorization Method for Multiscale Simulations: A Review
Li, Mengmeng
Ding, Dazhi
Heldring, Alexander
Hu, Jun
Chen, Rushan
Vecchi, Giuseppe
IEEE OPEN JOURNAL OF ANTENNAS AND PROPAGATION, 2021, 2 : 286 - 301
[43] A hybrid algorithm for low-rank approximation of nonnegative matrix factorization
Wang, Peitao
He, Zhaoshui
Xie, Kan
Gao, Junbin
Antolovich, Michael
Tan, Beihai
NEUROCOMPUTING, 2019, 364 : 129 - 137
[44] Low-rank matrix factorization with nonconvex regularization and bilinear decomposition
Wang, Sijie
Xia, Kewen
Wang, Li
Yin, Zhixian
He, Ziping
Zhang, Jiangnan
Aslam, Naila
SIGNAL PROCESSING, 2022, 201
[45] Nonlocal low-rank matrix completion for image interpolation using edge detection and neural network
Chen, Wei
Tian, Qichong
Liu, Jin
Wang, Qianping
SIGNAL IMAGE AND VIDEO PROCESSING, 2014, 8 (04) : 657 - 663
[46] Low-Rank Sinkhorn Factorization
Scetbon, Meyer
Cuturi, Marco
Peyre, Gabriel
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
[47] Nonlocal low-rank matrix completion for image interpolation using edge detection and neural network
Wei Chen
Qichong Tian
Jin Liu
Qianping Wang
Signal, Image and Video Processing, 2014, 8 : 657 - 663
[48] Reweighted Low-Rank Factorization With Deep Prior for Image Restoration
Chen, Lin
Jiang, Xue
Liu, Xingzhao
Haardt, Martin
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2022, 70 : 3514 - 3529
[49] Low-Rank Tensor Completion Using Matrix Factorization Based on Tensor Train Rank and Total Variation
Ding, Meng
Huang, Ting-Zhu
Ji, Teng-Yu
Zhao, Xi-Le
Yang, Jing-Hua
JOURNAL OF SCIENTIFIC COMPUTING, 2019, 81 (02) : 941 - 964
[50] Low-Rank Tensor Completion Using Matrix Factorization Based on Tensor Train Rank and Total Variation
Meng Ding
Ting-Zhu Huang
Teng-Yu Ji
Xi-Le Zhao
Jing-Hua Yang
Journal of Scientific Computing, 2019, 81 : 941 - 964

← 1 2 3 4 5 →