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
收藏
页码：1088 / 1091
页数：4
相关论文
共 36 条
  • [21] END-TO-END SPEECH RECOGNITION AND KEYWORD SEARCH ON LOW-RESOURCE LANGUAGES
    Rosenberg, Andrew
    Audhkhasi, Kartik
    Sethy, Abhinav
    Ramabhadran, Bhuvana
    Picheny, Michael
    2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 5280 - 5284
  • [22] A semi-supervised recurrent neural network for video salient object detection
    Kompella, Aditya
    Kulkarni, Raghavendra, V
    NEURAL COMPUTING & APPLICATIONS, 2021, 33 (06) : 2065 - 2083
  • [23] End-to-end keyword search system based on attention mechanism and energy scorer for low resource languages
    Zhao, Zeyu
    Zhang, Wei-Qiang
    NEURAL NETWORKS, 2021, 139 : 326 - 334
  • [24] USING WORD BURST ANALYSIS TO RESCORE KEYWORD SEARCH CANDIDATES ON LOW-RESOURCE LANGUAGES
    Richards, Justin
    Ma, Min
    Rosenberg, Andrew
    2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
  • [25] Resources and Benchmarks for Keyword Search in Spoken Audio From Low-Resource Indian Languages
    Nadimpalli, Vijaya Lakshmi V.
    Kesiraju, Santosh
    Banka, Rohith
    Kethireddy, Rashmi
    Gangashetty, Suryakanth, V
    IEEE ACCESS, 2022, 10 : 34789 - 34799
  • [26] A semi-supervised production scheduling method based on co-training deep neural network for smart shop floors
    Ma, Yumin
    Shi, Jiaxuan
    Cai, Jingwen
    Liu, Juan
    Qiao, Fei
    Liao, Yipeng
    COMPUTERS & INDUSTRIAL ENGINEERING, 2024, 194
  • [27] SEMI-SUPERVISED LEARNING WITH DEEP NEURAL NETWORKS FOR RELATIVE TRANSFER FUNCTION INVERSE REGRESSION
    Wang, Ziteng
    Li, Junfeng
    Yan, Yonghong
    Vincent, Emmanuel
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 191 - 195
  • [28] Semi-Supervised Speaker Adaptation for In-Vehicle Speech Recognition with Deep Neural Networks
    Lee, Wonkyum
    Hang, Kyu J.
    Lane, Ian
    17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 3843 - 3847
  • [29] Improving RNN-T for Domain Scaling Using Semi-Supervised Training with Neural TTS
    Deng, Yan
    Zhao, Rui
    Meng, Zhong
    Chen, Xie
    Liu, Bing
    Li, Jinyu
    Gong, Yifan
    He, Lei
    INTERSPEECH 2021, 2021, : 751 - 755
  • [30] Semi-supervised and Cross-lingual Knowledge Transfer Learnings for DNN Hybrid Acoustic Models under Low-resource Conditions
    Xu, Haihua
    Su, Hang
    Ni, Chongjia
    Xiao, Xiong
    Huang, Hao
    Chng, Eng-Siong
    Li, Haizhou
    17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 1315 - 1319
1234