Feature selection of mime speech recognition using surface electromyography data

被引:0
|
作者
Zhang, Ming [1 ]
Zhang, Wei [1 ]
Zhang, Bixuan [1 ]
Wang, You [1 ]
Li, Guang [1 ]
机构
[1] Zhejiang Univ, Inst Cyber Syst & Control, Coll Control Sci & Engn, Zheda Rd 38, Hangzhou 310027, Peoples R China
关键词
Mime speech recognition(MSR); Surface electromyography(sEMG); feature extraction; random forest; STATE;
D O I
10.1109/cac48633.2019.8996646
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Surface electromyography (sEMG) is a potential technique and resolution to information transmission and communication problems in noise surroundings as well as military environment. By capturing facial sEMG signals from several particular articulatory muscles, this study aims to find out features and patterns underlying sEMG data, thus decoding the speech information. In this paper, mime speech recognition on ten Chinese characters using random forest (RF) algorithm is accomplished and multiple patterns have been effectively recognized. Interpolation and alignment are applied to improve the recognition accuracy for sEMG signals with the same label. The sEMG signals are quite different in both fluctuation and span length, thus making data split and segmentation of raw data necessary. After data preprocessing, overlapped windowing techniques, which requires opportune window length and shifts, has been used to extract sEMG features. To explore proper method and feature combinations that can yield satisfactory performance, recognition results of various classification methods are compared. As an ensemble learning algorithm, random forest method is used to predict speech information and give recognition results. Experimental outcomes have indicated that the method of bicubic interpolation, alignment and windowing yields recognition accuracy that outperform other competing approaches. Classification results further demonstrate the combination of overlapped windowing technique and random forest algorithm is effective on mine speech recognition tasks.
引用
收藏
页码:3173 / 3178
页数:6
相关论文
共 50 条
  • [1] Mutual Information analysis for feature and sensor subset selection in surface electromyography based speech recognition
    Sridhar, Vivek Kumar Rangarajan
    Prasad, Rohit
    Natarajan, Prem
    11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2, 2010, : 1205 - 1208
  • [2] Feature Selection for Myoelectric Pattern Recognition using Two Channel Surface Electromyography Signals
    Powar, Omkar S.
    Chemmangat, Krishnan
    TENCON 2017 - 2017 IEEE REGION 10 CONFERENCE, 2017, : 1022 - 1026
  • [3] Towards Continuous Speech Recognition Using Surface Electromyography
    Jou, Szu-Chen
    Schultz, Tanja
    Walliczek, Matthias
    Kraft, Florian
    Waibel, Alex
    INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 573 - +
  • [4] Small-vocabulary speech recognition using surface electromyography
    Betts, Bradley J.
    Binsted, Kim
    Jorgensen, Charles
    INTERACTING WITH COMPUTERS, 2006, 18 (06) : 1242 - 1259
  • [5] Convolutional Neural Network applied in mime speech recognition using sEMG data
    Ai, Qing
    Zhang, Wei
    Zhang, Bixuan
    Li, Guang
    Yang, Meng
    2019 CHINESE AUTOMATION CONGRESS (CAC2019), 2019, : 3347 - 3352
  • [6] Attention Bidirectional LSTM Networks Based Mime Speech Recognition Using sEMG Data
    Ye, Hongyi
    Lin, Haohong
    Song, Zijun
    Zhang, Ming
    Hu, Ruifen
    Li, Nan
    Li, Guang
    2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2020, : 3162 - 3167
  • [7] Silent Speech Recognition Based on Surface Electromyography
    Ma, Siyuan
    Jin, Dantong
    Zhang, Ming
    Zhang, Bixuan
    Wang, You
    Li, Guang
    Yang, Meng
    2019 CHINESE AUTOMATION CONGRESS (CAC2019), 2019, : 4497 - 4501
  • [8] Preprocessing Improvement in Mime Speech Recognition based on Surface Electromyogram
    Li, Huiyan
    Zhang, Ming
    Li, Guang
    Hu, Ruifen
    Zhang, Bixuan
    2019 CHINESE AUTOMATION CONGRESS (CAC2019), 2019, : 3465 - 3470
  • [9] Feature Selection for Vowel Recognition Based on Surface Electromyography Derived with Multichannel Electrode Grid
    Kubo, Takatomi
    Yoshida, Masaki
    Hattori, Takumu
    Ikeda, Kazushi
    INTELLIGENT SCIENCE AND INTELLIGENT DATA ENGINEERING, ISCIDE 2011, 2012, 7202 : 242 - 249
  • [10] Discriminative feature selection for speech recognition
    Bocchieri, E.L.
    Wilpon, J.G.
    Computer Speech and Language, 1993, 7 (03): : 229 - 246