Mandarin Digits Speech Recognition Using Support Vector Machines

被引：2
|
作者：
谢湘
匡镜明
机构：
[1] Beijing Institute of Technology
[2] Beijing100081
[3] China
[4] School of Information Science and Technology
来源：
Journal of Beijing Institute of Technology | 2005年 / 01期
关键词：
speech recognition; support vector machine (SVM); kernel function;
D O I：
10.15918/j.jbit1004-0579.2005.01.003
中图分类号：
TN912.3 [语音信号处理];
学科分类号：
0711 ;
摘要：
A method of applying support vector machine (SVM) in speech recognition was proposed, and a speech recognition system for mandarin digits was built up by SVMs. In the system, vectors were linearly extracted from speech feature sequence to make up time-aligned input patterns for SVM, and the decisions of several 2-class SVM classifiers were employed for constructing an N-class classifier. Four kinds of SVM kernel functions were compared in the experiments of speaker-independent speech recognition of mandarin digits. And the kernel of radial basis function has the highest accurate rate of 99.33%, which is better than that of the baseline system based on hidden Markov models (HMM) (97.08%). And the experiments also show that SVM can outperform HMM especially when the samples for learning were very limited.
引用
收藏
页码：9 / 12
页数：4
相关论文
共 50 条
  • [21] Whispered Speech Recognition using Hidden Markov Models and Support Vector Machines
    Galic, Jovan
    Popovic, Branislav
    Pavlovic, Dragana Sumarac
    [J]. ACTA POLYTECHNICA HUNGARICA, 2018, 15 (05) : 11 - 29
  • [22] Support vector machines in handwritten digits classification
    Markowska-Kaczmar, U
    Kubacki, P
    [J]. 5th International Conference on Intelligent Systems Design and Applications, Proceedings, 2005, : 406 - 411
  • [23] On the Optimization of Multiclass Support Vector Machines Dedicated to Speech Recognition
    Mezzoudj, Freha
    Benyettou, Assia
    [J]. NEURAL INFORMATION PROCESSING, ICONIP 2012, PT II, 2012, 7664 : 1 - 8
  • [24] Recognition of bimodal produced speech based on Support Vector Machines
    Galic, Jovan
    Pavlovic, Dragana Sumarac
    Jovicic, Slobodan T.
    Markovic, Branko
    Grozdic, Dorde
    [J]. 2017 25TH TELECOMMUNICATION FORUM (TELFOR), 2017, : 362 - 365
  • [25] Bagged support vector machines for emotion recognition from speech
    Bhavan, Anjali
    Chauhan, Pankaj
    Hitkul
    Shah, Rajiv Ratn
    [J]. KNOWLEDGE-BASED SYSTEMS, 2019, 184
  • [26] Mixture of Support Vector Machines for HMM based speech recognition
    Krueger, Sven E.
    Schaffoener, Martin
    Katz, Marcel
    Andelic, Edin
    Wendemuth, Andreas
    [J]. 18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 4, PROCEEDINGS, 2006, : 326 - +
  • [27] An overview of speech recognition system based on the Support Vector Machines
    Sonkamble, Balwant A.
    Doye, D. D.
    [J]. 2008 INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION ENGINEERING, VOLS 1-3, 2008, : 768 - +
  • [28] Application of Support Vector Machines classifiers to visual speech recognition
    Gordan, M
    Kotropoulos, C
    Pitas, I
    [J]. 2002 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL III, PROCEEDINGS, 2002, : 129 - 132
  • [29] Design and Evaluation of Speech based Emotion Recognition System using Support Vector Machines
    Harshini, D.
    Pranjali, B.
    Ranjitha, M.
    Rushali, J.
    Manikandan, J.
    [J]. 2019 IEEE 16TH INDIA COUNCIL INTERNATIONAL CONFERENCE (IEEE INDICON 2019), 2019,
  • [30] Acoustic model combination for recognition of speech in multiple languages using support vector machines
    Gangashetty, SV
    Sekhar, CC
    Yegnanarayana, B
    [J]. 2004 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2004, : 3065 - 3069
12345