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

[1] Learning and Compressing: Low-Rank Matrix Factorization for Deep Neural Network Compression
Cai, Gaoyuan
Li, Juhu
Liu, Xuanxin
Chen, Zhibo
Zhang, Haiyan
APPLIED SCIENCES-BASEL, 2023, 13 (04):
[2] Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks
Povey, Daniel
Cheng, Gaofeng
Wang, Yiming
Li, Ke
Xu, Hainan
Yarmohamadi, Mahsa
Khudanpur, Sanjeev
19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 3743 - 3747
[3] 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 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 6655 - 6659
[4] Low-Rank Matrix Completion Using Graph Neural Network
Luong Trung Nguyen
Shim, Byonghyo
11TH INTERNATIONAL CONFERENCE ON ICT CONVERGENCE: DATA, NETWORK, AND AI IN THE AGE OF UNTACT (ICTC 2020), 2020, : 17 - 21
[5] Denoising of Hyperspectral Image Using Low-Rank Matrix Factorization
Xu, Fei
Chen, Yongyong
Peng, Chong
Wang, Yongli
Liu, Xuefeng
He, Guoping
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2017, 14 (07) : 1141 - 1145
[6] On the Minimal Problems of Low-Rank Matrix Factorization
Jiang, Fangyuan
Oskarsson, Magnus
Astrom, Kalle
2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 2549 - 2557
[7] Structural Identifiability in Low-Rank Matrix Factorization
Fritzilas, Epameinondas
Milanic, Martin
Rahmann, Sven
Rios-Solis, Yasmin A.
ALGORITHMICA, 2010, 56 (03) : 313 - 332
[8] Adaptive quantile low-rank matrix factorization
Xu, Shuang
Zhang, Chun-Xia
Zhang, Jiangshe
PATTERN RECOGNITION, 2020, 103
[9] Structural Identifiability in Low-Rank Matrix Factorization
Epameinondas Fritzilas
Martin Milanič
Sven Rahmann
Yasmin A. Rios-Solis
Algorithmica, 2010, 56 : 313 - 332
[10] Dropout as a Low-Rank Regularizer for Matrix Factorization
Cavazza, Jacopo
Haeffele, Benjamin D.
Lane, Connor
Morerio, Pietro
Murino, Vittorio
Vidal, Rene
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 84, 2018, 84

← 1 2 3 4 5 →