Neural network ensemble based on vowel classification for chinese speaker recognition

被引:0
|
作者
Qian, Bo [1 ]
Tang, Zhen-min [1 ]
Li, Yan-ping [1 ]
Xu, Li-min [1 ]
Zhang, Yan [1 ,2 ]
机构
[1] Nanjing Univ Sci & Technol, Sch Comp S&T, Nanjing, Peoples R China
[2] Jinling Inst Techonol, Jiangsu Sheng, Peoples R China
关键词
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
As we known, features of speech signal not only reflect the identity information, but also contain the semantical information. In this paper, we describe a novel neural network ensemble architecture based on the finding that the diphthong and multi-vowel in Chinese can approximately be considered as the complex of mono-vowel and transitional pan in the standpoint of short-term analysis. Several neural networks are trained, each for the eigenspace of one mono-vowel, and their results are combined by another combinational neural network. The architecture can effectively improve the recognition accuracy by eliminating the disturbance of semantical information. Experimental results show that the recognition accuracy of our proposed approach is higher than conventional methods such as a single neural network and other proposed ensemble structures.
引用
收藏
页码:141 / +
页数:3
相关论文
共 50 条
  • [41] Facial Expression Classification Based on Ensemble Convolutional Neural Network
    Zhou Tao
    Lu Xiaoqi
    Ren Guoyin
    Gu Yu
    Zhang Ming
    Li Jing
    LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (14)
  • [42] Ship Classification Based on Multifeature Ensemble with Convolutional Neural Network
    Shi, Qiaoqiao
    Li, Wei
    Tao, Ran
    Sun, Xu
    Gao, Lianru
    REMOTE SENSING, 2019, 11 (04)
  • [43] Hindi vowel recognition using artificial neural network
    Government Engineering Coll
    Adv Modell Anal B Signals Inf Data Patterns, 1-3 (49-58):
  • [44] Application of Ensemble Network Architecture Based on Convolutional Neural Network in Image Classification
    Yu, Zhuocheng
    Zhang, Zhiqiang
    Li, Kehan
    Wang, Le
    2021 2ND INTERNATIONAL CONFERENCE ON BIG DATA & ARTIFICIAL INTELLIGENCE & SOFTWARE ENGINEERING (ICBASE 2021), 2021, : 452 - 455
  • [45] Chinese Sentence Classification Based on Convolutional Neural Network
    Gu, Chengwei
    Wu, Ming
    Zhang, Chuang
    2017 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE APPLICATIONS AND TECHNOLOGIES (AIAAT 2017), 2017, 261
  • [46] A TEXT-INDEPENDENT SPEAKER RECOGNITION SYSTEM BASED ON VOWEL SPOTTING
    FAKOTAKIS, N
    TSOPANOGLOU, A
    KOKKINAKIS, G
    SPEECH COMMUNICATION, 1993, 12 (01) : 57 - 68
  • [47] A novel approach for speaker recognition by vowel specking
    Nasir, Sarwat
    Khokar, Imtiaz
    Jafri, M. N.
    PROCEEDINGS OF THE NINTH IASTED INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING, 2007, : 162 - 166
  • [48] Speaker recognition method with high-order neural network based on biomimetics pattern recognition
    Wu, Yan
    Jin, Mingxi
    Wang, Shoujue
    Jisuanji Gongcheng/Computer Engineering, 2006, 32 (12): : 184 - 186
  • [49] Neural network and GMM based feature mappings for consonant–vowel recognition in emotional environment
    Yadav J.
    Rao K.S.
    International Journal of Speech Technology, 2018, 21 (3) : 421 - 433
  • [50] Ground Nephogram Recognition Algorithm Based on Selective Neural Network Ensemble
    Li, Tao
    Li, Xiang
    Ren, Yongjun
    Xia, Jinyue
    CMC-COMPUTERS MATERIALS & CONTINUA, 2020, 63 (02): : 621 - 631