An improved Mandarin keyword spotting system using mce training and context-enhanced verification

被引：0
|
作者：
Liang, JiaEn [1 ]
Meng, Meng [1 ]
Wang, XiaoRui [1 ]
Ding, Peng [1 ]
Xu, Bo [1 ]
机构：
[1] Chinese Acad Sci, Inst Automat, Beijing 100080, Peoples R China
来源：
2006 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-13 | 2006年
关键词：
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
The task of keyword spotting is to detect a set of keywords in the input continuous speech. The main goal of this work is to develop an improved mandarin keyword spotting (KWS) system for conversational telephone speech (CTS). In this paper, we propose an efficient online-garbage model based KWS system, which integrated with a word-level minimum classification error (MCE) training method and a novel context-enhanced verification method. Experiment showed that the proposed methods can reduce the Equal-Error-Rate (EER) of the system by 13.8% in relative.
引用
下载
收藏
页码：1145 / 1148
页数：4
相关论文
共 50 条
  • [21] Improved Keyword Spotting System by Optimizing Posterior Confidence Measure Vector Using Feed-forward Neural Network
    Liu, Yuchen
    Xu, Mingxing
    Cai, Lianhong
    PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2014, : 2036 - 2041
  • [22] FEASIBILITY EVALUATION FOR KEYWORD SPOTTING SYSTEM USING MINI MICROPHONE ARRAY ON UAV
    Andra, Muhammad Bagus
    Rohman, Budiman P. A.
    Usagawa, Tsuyoshi
    2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 2264 - 2267
  • [23] Improved bottleneck feature using hierarchical deep belief networks for keyword spotting in continues speech
    1600, Science and Engineering Research Support Society, 20 Virginia Court, Sandy Bay, Tasmania, Australia (06):
  • [24] Thinking space generation using context-enhanced knowledge fusion for systematic brain computing
    Kuai, Hongzhi
    Tao, Xiaohui
    Zhong, Ning
    WEB INTELLIGENCE, 2023, 21 (04) : 345 - 361
  • [25] Keyword Spotting System for Tamil Isolated Words using Multidimensional MFCC and DTW Algorithm
    Senthildevi, K. A.
    Chandra, E.
    2015 INTERNATIONAL CONFERENCE ON COMMUNICATIONS AND SIGNAL PROCESSING (ICCSP), 2015, : 550 - 554
  • [26] Energy-friendly keyword spotting system using add-based convolution
    Zhou, Hang
    Hu, Wenchao
    Yeung, Yu Ting
    Chen, Xiao
    INTERSPEECH 2021, 2021, : 4234 - 4238
  • [27] A Pitch and Noise Robust Keyword Spotting System Using SMAC Features with Prosody Modification
    Maity, Karabi
    Pradhan, Gayadhar
    Singh, Jyoti Prakash
    CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2021, 40 (04) : 1892 - 1904
  • [28] A Pitch and Noise Robust Keyword Spotting System Using SMAC Features with Prosody Modification
    Karabi Maity
    Gayadhar Pradhan
    Jyoti Prakash Singh
    Circuits, Systems, and Signal Processing, 2021, 40 : 1892 - 1904
  • [29] Keyword Spotting System using Low-complexity Feature Extraction and Quantized LSTM
    Herisse, Kevin
    Larras, Benoit
    Frappe, Antoine
    Kaiser, Andreas
    2021 28TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS, AND SYSTEMS (IEEE ICECS 2021), 2021,
  • [30] OPTIMIZE WHAT MATTERS: TRAINING DNN-HMM KEYWORD SPOTTING MODEL USING END METRIC
    Shrivastava, Ashish
    Kundu, Arnav
    Dhir, Chandra
    Naik, Devang
    Tuzel, Oncel
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 4000 - 4004
12345