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

[21] A Semi-supervised Graph Deep Neural Network for Automatic Protein Function Annotation
Sellami, Akrem
Sarker, Bishnu
Tabbone, Salvatore
Devignes, Marie-Dominique
Aridhi, Sabeur
BIOINFORMATICS AND BIOMEDICAL ENGINEERING, PT II, 2022, : 153 - 166
[22] A Deep Neural Network Based on ELM for Semi-supervised Learning of Image Classification
Chang, Peiju
Zhang, Jiangshe
Hu, Junying
Song, Zengjie
NEURAL PROCESSING LETTERS, 2018, 48 (01) : 375 - 388
[23] Semi-supervised Named Entity Recognition for Low-Resource Languages Using Dual PLMs
Yohannes, Hailemariam Mehari
Lynden, Steven
Amagasa, Toshiyuki
Matono, Akiyoshi
NATURAL LANGUAGE PROCESSING AND INFORMATION SYSTEMS, PT I, NLDB 2024, 2024, 14762 : 166 - 180
[24] Semi-supervised word polarity identification in resource-lean languages
Dehdarbehbahani, Iman
Shakery, Azadeh
Faili, Heshaam
NEURAL NETWORKS, 2014, 58 : 50 - 59
[25] SEMI-SUPERVISED TRAINING STRATEGIES FOR DEEP NEURAL NETWORKS
Gibson, Matthew
Cook, Gary
Zhan, Puming
2017 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2017, : 77 - 83
[26] Improved Classification with Semi-supervised Deep Belief Network
Wang, Gongming
Qiao, Junfei
Li, Xiaoli
Wang, Lei
Qian, Xiaolong
IFAC PAPERSONLINE, 2017, 50 (01): : 4174 - 4179
[27] Semi-supervised Deep Learning for Network Anomaly Detection
Sun, Yuanyuan
Guo, Lili
Li, Ye
Xu, Lele
Wang, Yongming
ALGORITHMS AND ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP 2019, PT II, 2020, 11945 : 383 - 390
[28] Semi-supervised Deep Network Representation with Text Information
Ming, Xinchun
Hu, Fangyu
2017 12TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS AND KNOWLEDGE ENGINEERING (IEEE ISKE), 2017,
[29] Cybercrime Detection Using Semi-Supervised Neural Network
Karimi, Abbas
Abbasabadei, Saber
Torkestani, Javad Akbari
Zarafshan, Faraneh
COMPUTER SCIENCE JOURNAL OF MOLDOVA, 2021, 29 (02) : 155 - 183
[30] 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 (02) : 171 - 184

← 1 2 3 4 5 →