Support Vector Machines with the Priorities Method for Speaker Independent Phoneme Recognition

被引：0
|
作者：
Cutajar, M. [1 ]
Gatt, E. [1 ]
Grech, I [1 ]
Casha, O. [1 ]
Micallef, J. [1 ]
机构：
[1] Univ Malta, Fac ICT, Dept Microelect & Nanoelect, Msida 2080, Malta
来源：
2011 IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY (ISSPIT) | 2011年
关键词：
phoneme recognition; speaker-independent; multiclass support vector machines; priorities method;
D O I：
暂无
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
A speaker independent phoneme recognition system, based on Support Vector Machines (SVMs) method was improved by adding a priority scheme to forecast the three most likely phonemes. The system helps improve the obtained recognitions rate. For the phoneme recognition system, four multiclass SVMs methods, the All-at-once, One-against-all, One-against-one, and the Directed Acyclic Graph SVM (DAGSVM), were designed. The One-against-one method performed best, achieving an accuracy of 53.70%. This accuracy was further increased to 75.41%, when the second and third priorities were considered in the priorities method. All tests were carried out on the TIMIT database.
引用
收藏
页码：409 / 414
页数：6
相关论文
共 50 条
  • [31] Speaker independent speech recognition method with constrained time alignment near phoneme discriminative frame
    Konuma, T
    Suzuki, T
    Yamada, M
    Ohno, Y
    Hoshimi, M
    Niyada, K
    [J]. 1997 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, PROCEEDINGS, 1997, : 458 - 465
  • [32] Speaker Recognition Based on Support Vector Machines and Multi-scale Wavelet Analysis
    Zhang, Zhenling
    Jia, Yangli
    Xie, Shengxian
    Zhang, Min
    [J]. 2009 INTERNATIONAL SYMPOSIUM ON COMPUTER NETWORK AND MULTIMEDIA TECHNOLOGY (CNMT 2009), VOLUMES 1 AND 2, 2009, : 430 - 433
  • [33] Score calibrating for speaker recognition based on support vector machines and Gaussian Mixture Models
    Katz, Marcel
    Schaffoener, Martin
    Krueger, Sven E.
    Wendemuth, Andreas
    [J]. PROCEEDINGS OF THE NINTH IASTED INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING, 2007, : 146 - 151
  • [34] Support Vector Machines for Speaker Based Speech Indexing
    Moattar, M. H.
    Homayounpour, M. M.
    [J]. 2009 14TH INTERNATIONAL COMPUTER CONFERENCE, 2009, : 606 - 611
  • [35] SPEAKER-INDEPENDENT SPOKEN WORD RECOGNITION SYSTEM BASED ON PARALLEL PHONEME LABELING (PPL) METHOD
    IMAI, S
    TANIGUCHI, I
    KAWASAKI, T
    FURUICHI, C
    DOI, H
    [J]. ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE, 1994, 77 (09): : 42 - 53
  • [36] On Text-independent Speaker Recognition via Improved Vector Quantization Method
    Liu Ting-ting
    Guan Sheng-xiao
    [J]. 2013 32ND CHINESE CONTROL CONFERENCE (CCC), 2013, : 3912 - 3916
  • [37] Efficient Speaker Recognition based on Multi-class Twin Support Vector Machines and GMMs
    Cong, Hanhan
    Yang, Chengfu
    Pu, Xiaorong
    [J]. 2008 IEEE CONFERENCE ON ROBOTICS, AUTOMATION, AND MECHATRONICS, VOLS 1 AND 2, 2008, : 614 - 618
  • [38] Support Vector Domain Description for speaker recognition
    Xin, D
    Wu, ZH
    Zhang, WF
    [J]. NEURAL NETWORKS FOR SIGNAL PROCESSING XI, 2001, : 481 - 488
  • [39] Support vector machines for face recognition
    Guo, GD
    Li, SZ
    Chan, KL
    [J]. IMAGE AND VISION COMPUTING, 2001, 19 (9-10) : 631 - 638
  • [40] Iris recognition with support vector machines
    Roy, K
    Hattacharya, P
    [J]. ADVANCES IN BIOMETRICS, PROCEEDINGS, 2006, 3832 : 486 - 492
12345