UNSUPERVISED LEARNING ALGORITHM FOR VOWEL TEMPLATES BASED ON MINIMUM QUANTIZATION DISTORTION.

被引：0
|
作者：
Sugiyama, Masahide
Shikano, Kiyohiro
机构：
来源：
Reports of the Electrical Communication Laboratory | 1986年 / 34卷 / 03期
关键词：
MATHEMATICAL TECHNIQUES - Algorithms - SYSTEMS SCIENCE AND CYBERNETICS - Learning Systems;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
A new unsupervised learning algorithm is proposed for speaker-independent speech recognition. The algorithm is formulated as a problem involving selection of an optimum vowel template set from pre-stored sets based on minimum quantization distortion. This algorithm has two advantages: learning is unsupervised, and learning and recognition are accomplished simultaneously. To evaluate this algorithm, word recognition experiments focusing upon 100 city names were carried out for 30 males and 20 females.
引用
收藏
页码：357 / 362
相关论文
共 50 条
  • [1] UNSUPERVISED LEARNING ALGORITHM FOR VOWEL TEMPLATES BASED ON MINIMUM QUANTIZATION DISTORTION
    SUGIYAMA, M
    SHIKANO, K
    REVIEW OF THE ELECTRICAL COMMUNICATIONS LABORATORIES, 1986, 34 (03): : 357 - 362
  • [2] UNSUPERVISED LEARNING ALGORITHM FOR VOWEL TEMPLATES BASED ON QUANTIZATION DISTORTION MINIMUM PRINCIPLE.
    Sugiyama, Masahide
    Shikano, Kiyohiro
    Denki Tsushin Kenkyujo kenkyu jitsuyoka hokoku, 1985, 34 (12): : 1717 - 1725
  • [3] AN IMPROVEMENT OF THE MINIMUM DISTORTION ENCODING ALGORITHM FOR VECTOR QUANTIZATION
    BEI, CD
    GRAY, RM
    IEEE TRANSACTIONS ON COMMUNICATIONS, 1985, 33 (10) : 1132 - 1133
  • [4] ON A NOVEL UNSUPERVISED COMPETITIVE LEARNING ALGORITHM FOR SCALAR QUANTIZATION
    VANHULLE, MM
    MARTINEZ, D
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (03): : 498 - 501
  • [5] A new unsupervised competive learning algorithm for vector quantization
    Lin, TC
    Yu, PT
    ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE, 2002, : 944 - 948
  • [6] On a novel unsupervised competitive learning algorithm for scalar quantization - Comment
    Andrew, LLH
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (01): : 254 - 256
  • [7] Relevance Learning in Unsupervised Vector Quantization Based on Divergences
    Kaestner, Marika
    Backhaus, Andreas
    Geweniger, Tina
    Haase, Sven
    Seiffert, Udo
    Villmann, Thomas
    ADVANCES IN SELF-ORGANIZING MAPS, WSOM 2011, 2011, 6731 : 90 - 100
  • [8] PARTIAL-DISTORTION-WEIGHTED FUZZY COMPETITIVE LEARNING ALGORITHM FOR VECTOR QUANTIZATION
    ZHU, C
    LI, LH
    WANG, TJ
    HE, ZY
    ELECTRONICS LETTERS, 1994, 30 (06) : 505 - 506
  • [9] Unsupervised learning algorithm based on data driving
    Liu, Kai-Di
    Pang, Yan-Jun
    Zhou, Shao-Ling
    Li, Wen-Guo
    Kongzhi yu Juece/Control and Decision, 2009, 24 (03): : 472 - 476
  • [10] Unsupervised learning for a clustering algorithm based on ellipsoidal calculus
    Guarneros, Alejandro
    Salgado, Ivan
    Chairez, Isaac
    2020 7TH INTERNATIONAL CONFERENCE ON CONTROL, DECISION AND INFORMATION TECHNOLOGIES (CODIT'20), VOL 1, 2020, : 124 - 129
12345