Journal of Jilin University(Engineering and Technology Edition) ›› 2024, Vol. 54 ›› Issue (10): 3050-3057.doi: 10.13229/j.cnki.jdxbgxb.20221587

Previous Articles    

Feature extraction of speech signals of exoskeleton devices in noise environments

Wen-jie CHEN1,2(),Zhen-xing SU1,2,Xian-tao SUN1,2,Yuan-yuan LIU1,Xiang-tao HU1,Ya-li ZHI1   

  1. 1.School of Electrical Engineering and Automation，Anhui University，Hefei 230601，China
    2.Anhui Engineering Laboratory of Human-Robot Collaboration System and Intelligent Equipment，Anhui University，Hefei 230601，China
  • Received:2022-12-12 Online:2024-10-01 Published:2024-11-22

RICH HTML

 1   

PDF (PC)

185

Abstract:

In actual working environments， exoskeleton devices for speech systems have poor voice command recognition performance due to the influence of environmental noise. This paper presents speech characteristics based on the Gammatone Frequency Cepstrum Coefficient using discrete orthogonal Stockwell transform. Time domain information of speech signal energy and zero crossing rate is characterized by discrete path transformation and composed into hybrid features. Redundancy， irrelevance， and information complementarity between the features are considered under low signal-to-noise ratios. The improved correlation fast filtering feature selection algorithm is used to obtain the optimal feature subset for the voice system of exoskeleton device control commands. Experimental results show that the optimized hybrid features are more robust under low signal-to-noise ratios， and the recognition rate of traditional Mel cepstral coefficients improves by about 20% under pink noise with zero signal-to-noise ratios.

Key words: exoskeleton devices, discrete orthogonal Stockwell transform, discrete path transformation, feature selection, feature extraction

CLC Number: 

  • TN912.3

Fig.1

DOST base function（ν=12，β=8）"

Fig.2

Spectrogram of FDOST"

Fig.3

DPT response diagrams of different signals"

Fig.4

FCBF algorithm flow chart"

Fig.5

Flow chart of SFGFCC+DPT algorithm"

Fig.6

Exoskeleton device"

Fig.7

Experimental diagram"

Table 1

Recognition rates of different characteristicparameters in noiseless environment"

特征参数无噪环境识别率/%
MFCC93.6
GFCC93.2
SFGFCC94.8
SFGFCC+DPT95.1

Fig.8

Pink noise"

Fig.9

Factory noise"

Fig.10

Machine gun noise"

Fig.11

Destroyer engine room noise"

1 Shaik R, Venkatramaphanikumar S. Sentiment analysiswith word-based Urdu speech recognition[J]. Journal of Ambient Intelligence and Humanized Computing, 2022, 13(5): 2511-2531.
2 Goyal K, Singh A, Kadyan V. A comparison of laryngeal effect in the dialects of Punjabi language[J]. Journal of Ambient Intelligence and Humanized Computing, 2022, 13(5): 2415-2428.
3 Al-Karawi K A, Mohammed D Y. Improving short utterance speaker verification by combining MFCC and entrocy in noisy conditions[J]. Journal of Multimedia Tools and Applications, 2021, 80(14): 22231-22249.
4 Kadyan V, Bawa P, Hasija T. In domain training data augmentation on noise robust Punjabi children speech recognition[J]. Journal of Ambient Intelligence and Humanized Computing, 2022,13: 2705-2721.
5 刘国华, 周文斌. 基于卷积神经网络的脉搏波时频域特征混叠分类[J]. 吉林大学学报:工学版, 2020, 50(5): 1818-1825.
Liu Guo-hua, Zhou Wen-bin. Pulse wave signal classification algorithm based on time frequency domain feature aliasing using convolutional neural network[J]. Journal of Jilin University(Engineering and Technology Edition), 2020,50(5): 1818-1825.
6 Wei D, Zhang Y, Li Y M. Linear canonical stockwell transform: theory and applications[J]. IEEE Transactions on Signal Processing, 2022, 70: 1333-1347.
7 李海峰, 房春英, 马琳, 等. 病理语音的S变换特征[J]. 清华大学学报:自然科学版, 2016, 56(7): 765-771.
Li Hai-feng, Fang Chun-ying, Ma Lin, et al. S-transform feature for pathological speech[J]. Journal of Tsinghua University(Science & Technology), 2016, 56(7): 765-771.
8 袁莉芬, 李松, 尹柏强, 等. 基于自适应快速S变换和 XGBoost的心电信号精确快速分类方法[J]. 电子与信息学报, 2023, 45(4): 1464-1474.
Yuan Li-fen, Li Song, Yin Bai-qiang, et al. Accurate and fast electrocardiogram classification method based on adaptive fast S-Transform and XGBoost[J]. Journal of Electronics and Information,2023, 45(4): 1464-1474.
9 李峰, 陈皖皖, 杨义. 基于稀疏自适应S变换和深度残差网络的轴承故障诊断方法[J]. 电机与控制学报, 2022, 26(8):112-119.
Li Feng, Chen Wan-wan, Yang Yi. Research on bearing fault diagnosis based on sparse adaptive S-transform and deep residual network[J]. Electric Machines and Control, 2022, 26(8): 112-119.
10 Karheily S,  Moukadem A, Gourbo J B, et al. sEMG time-frequency features for hand movements classification[J]. Journal of Expert Systems with Applications,2022, 210: No.118282.
11 Wang Y, Orchard J. Fast discrete orthonormal stockwell transform[J]. SIAM Journal on Scientific Computing, 2009, 31(5): 4000-4012.
12 Guido R C, Pedroso F, Contreras R C, et al. Introducing the discrete path transform(DPT)and its applications in signal analysis, arte factremoval, and spoken word recognition[J]. Digital Signal Processing, 2021, 117: No.103158.
13 Şen B, Peker M. Novel approaches for auto mated epileptic diagnosis using FCBF selection and classifycation algorithms[J]. Turkish Journal of Electrical Engineering and Computer Sciences, 2013, 21(7): 2092-2109.
14 周镇镇. 离散余弦S变换及其在医学图像降噪中的应用研究[D]. 济南: 山东大学信息科学与工程学院, 2016.
Zhou Zhen-zhen. Discrete cosine S transform and its application in medical image denoising[D]. Jinan: School of Information Science and Engineering, Shandong University, 2016.
15 刘振宇. 基于语音的抑郁识别方法及关键技术研究[D].兰州: 兰州大学信息科学与工程学院, 2017.
Liu Zhen-yu. Research on method and key technology for depression recognition based on speech[D]. Lanzhou: School of Information Science & Engineering, Lanzhou University, 2017.
16 Kranthi Kumar L, Alphonse P J A. COVID-19 disease diagnosis with light-weight CNN using modified MFCC and enhanced GFCC from human respiratory sounds[J]. The European Physical Journal Special Topics, 2022, 231(18): 3329-3346.
[1] Dan-hui LAI,Wei-feng LUO,Xu-dong YUAN,Zi-liang QIU. Key point feature extraction algorithms for multimodal gesture in complex environments [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(8): 2288-2294.
[2] Yun-zuo ZHANG,Yu-xin ZHENG,Cun-yu WU,Tian ZHANG. Accurate lane detection of complex environment based on double feature extraction network [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(7): 1894-1902.
[3] Chang-jian WANG,Jiu-ming LIU,Jin-zhou ZHANG,Bin LI. Laser sequence pulse diagnosis method of planetary reducer fault based on high-speed photography technology [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(7): 1869-1875.
[4] Bo-song FAN,Chun-fu SHAO. Urban rail transit emergency risk level identification method [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(2): 427-435.
[5] Zhi-fei YANG,Jia ZHANG,Ze-yang LI. Node attack detection algorithm for complex networks based on incremental learning [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(10): 2963-2968.
[6] Feng-feng ZHOU,Tao YU,Yu-si FAN. Generative adversarial autoencoder integrated voting algorithm based on mass spectral data [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(10): 2969-2977.
[7] Shi-jun SONG,Min FAN. Design of big data anomaly detection model based on random forest algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(9): 2659-2665.
[8] En-shen LONG,Guang-ze BAN. Idle noise diagnosis algorithm of air-conditioning refrigeration compressor based on wavelet packet extraction [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(7): 1929-1934.
[9] Lin BAI,Lin-jun LIU,Xuan-ang LI,Sha WU,Ru-qing LIU. Depth estimation algorithm of monocular image based on self-supervised learning [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(4): 1139-1145.
[10] Feng-feng ZHOU,Zhen-wei YAN. A model for identifying neuropeptides by feature selection based on hybrid features [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(11): 3238-3245.
[11] Xiao-qi LYU,Hao LI,Yu GU. Adaptive blur and deduplication algorithm for digital media image based on wavelet domain [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(11): 3201-3206.
[12] Hui GUO,Jie-di FU,Zhen-dong LI,Yan YAN,Xiao LI. SVM parameters and feature selection optimization based on improved whale algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(10): 2952-2963.
[13] Pei-ze LI,Shi-shun ZHAO,Xiao-hui WENG,Xin-mei JIANG,Hong-bo CUI,Jian-lei QIAO,Zhi-yong CHANG. A new method for rapid detection of pesticide residues based on multi⁃sensor optimization [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(8): 1951-1956.
[14] Feng-feng ZHOU,Hai-yang ZHU. SEE： sense EEG⁃based emotion algorithm via three⁃step feature selection strategy [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(8): 1834-1841.
[15] Bin WANG,Bing-hui HE,Na LIN,Wei WANG,Tian-yang LI. Tea plantation remote sensing extraction based on random forest feature selection [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(7): 1719-1732.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd