English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 54907/89265 (62%)
造访人次 : 10600330      在线人数 : 22
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻

    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/50560

    题名: Robust Speaker Identification System Based on Two-Stage Vector Quantization
    作者: Chen, Wan-chen;謝景棠;Hsieh, Ching-tang;Hsu, Chih-hsu
    贡献者: 淡江大學電機工程學系
    关键词: Speaker Identification;Wavelet Transform;Linear Predictive Cepstral Coefficient (LPCC);2-Stage Vector Quantization
    日期: 2008-12-01
    上传时间: 2010-08-09 19:49:00 (UTC+8)
    出版者: 淡江大學
    摘要: This paper presents an effective method for speaker identification system. Based on the wavelet transform, the input speech signal is decomposed into several frequency bands, and then the linear predictive cepstral coefficients (LPCC) of each band are calculated. Furthermore, the cepstral mean normalization technique is applied to all computed features in order to provide similar parameter statistics in all acoustic environments. In order to effectively utilize these multi-band speech features, we propose a multi-band 2-stage vector quantization (VQ) as the recognition model in which different 2-stage VQ classifiers are applied independently to each band and the errors of all 2-stage VQ classifiers are combined to yield total error and a global recognition decision. Finally, the KING speech database is used to evaluate the proposed method for text-independent speaker identification. The experimental results show that the proposed method gives better performance than other recognition models proposed previously in both clean and noisy environments.
    關聯: 淡江理工學刊 = Tamkang Journal of Science and Engineering 11(4), pp.357-366
    DOI: 10.6180/jase.2008.11.4.05
    显示于类别:[電機工程學系暨研究所] 期刊論文


    档案 大小格式浏览次数
    1560-6686_11(4)p357-366.pdf2244KbAdobe PDF253检视/开启



    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回馈