Improving Semi-supervised Deep Neural Network. for Keyword Search in Low Resource Languages

被引：0

作者：

Hsiao, Roger ^{[1
]}

Ng, Tim ^{[1
]}

Le Zhang ^{[1
]}

Ranjan, Shivesh ^{[1
]}

机构：

[1] Raytheon BBN Technol, 10 Moulton St, Cambridge, MA 02138 USA

来源：

15TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2014), VOLS 1-4 | 2014年

关键词：

semi-supervised training; deep neural network; keyword search;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this work, we investigate how to improve semi-supervised DNN for low resource languages where the initial systems may have high error rate. We propose using semi-supervised MLP features for DNN training, and we also explore using confidence to improve semi-supervised cross entropy and sequence training. The work conducted in this paper was evaluated under the IARPA Babel program for the keyword spotting tasks. We focus on the limited condition where there are around 10 hours of supervised data for training.

引用

页码：1088 / 1091

页数：4

共 50 条

[31] Structural information aware deep semi-supervised recurrent neural network for sentiment analysis
Wenge Rong
Baolin Peng
Yuanxin Ouyang
Chao Li
Zhang Xiong
Frontiers of Computer Science, 2015, 9 : 171 - 184
[32] Semi-supervised Maximum Mutual Information Training of Deep Neural Network Acoustic Models
Manohar, Vimal
Povey, Daniel
Khudanpur, Sanjeev
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 2630 - 2634
[33] Structural information aware deep semi-supervised recurrent neural network for sentiment analysis
Rong, Wenge
Peng, Baolin
Ouyang, Yuanxin
Li, Chao
Xiong, Zhang
FRONTIERS OF COMPUTER SCIENCE, 2015, 9 (02) : 171 - 184
[34] Semi-supervised Deep Quantization for Cross-modal Search
Wang, Xin
Zhu, Wenwu
Liu, Chenghao
PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19), 2019, : 1730 - 1739
[35] Evolutionary Neural Architecture Search with Semi-supervised Accuracy Predictor
Xiao, Songyi
Zhao, Bo
Liu, Derong
2022 4TH INTERNATIONAL CONFERENCE ON CONTROL AND ROBOTICS, ICCR, 2022, : 28 - 32
[36] The 2016 RWTH Keyword Search System for Low-Resource Languages
Golik, Pavel
Tueske, Zoltan
Irie, Kazuki
Beck, Eugen
Schlueter, Ralf
Ney, Hermann
SPEECH AND COMPUTER, SPECOM 2017, 2017, 10458 : 719 - 730
[37] AN EMPIRICAL STUDY OF CONFUSION MODELING IN KEYWORD SEARCH FOR LOW RESOURCE LANGUAGES
Saraclar, Murat
Sethy, Abhinav
Ramabhadran, Bhuvana
Mangu, Lidia
Cui, Jia
Cui, Xiaodong
Kingsbury, Brian
Mamou, Jonathan
2013 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 2013, : 464 - 469
[38] IMPROVING SMALL CONVOLUTIONAL NEURAL NETWORKS WITH SEMI-SUPERVISED LEARNING
Badea, Mihai
Vertan, Constantin
Florea, Corneliu
Florea, Laura
Racoviteanu, Andrei
UNIVERSITY POLITEHNICA OF BUCHAREST SCIENTIFIC BULLETIN SERIES C-ELECTRICAL ENGINEERING AND COMPUTER SCIENCE, 2022, 84 (03): : 107 - 118
[39] IMPROVING SMALL CONVOLUTIONAL NEURAL NETWORKS WITH SEMI-SUPERVISED LEARNING
Badea, Mihai
Vertan, Constantin
Florea, Corneliu
Florea, Laura
Racoviţeanu, Andrei
UPB Scientific Bulletin, Series C: Electrical Engineering and Computer Science, 2022, 84 (03): : 107 - 118
[40] QUANTIFYING THE VALUE OF PRONUNCIATION LEXICONS FOR KEYWORD SEARCH IN LOW RESOURCE LANGUAGES
Chen, Guoguo
Khudanpur, Sanjeev
Povey, Daniel
Trmal, Jan
Yarowsky, David
Yilmaz, Oguz
2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 8560 - 8564

← 1 2 3 4 5 →