ASIA unversity:Item 310904400/78710
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 90437/105768 (86%)
造访人次 : 10940116      在线人数 : 632
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU 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
    ASIA unversity > 資訊學院 > 資訊傳播學系 > 會議論文 >  Item 310904400/78710


    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://asiair.asia.edu.tw/ir/handle/310904400/78710


    题名: C/V segmentation on mandarin speech signal via additional noise cascaded with Fourier-based speech enhancement system
    作者: 陸清達;Lu, Ching-Ta;王小川;Wang, Hsiao-Chuan
    贡献者: 資訊傳播學系
    日期: 2005.11
    上传时间: 2013-12-26 18:31:55 (UTC+8)
    摘要: An efficient and simple approach to segment the consonant and the vowel (C/V) speech signals by slightly corrupting a speech signal with white noise is proposed. This approach is based on the vowels are quasi-periodic, and the consonants can be regarded as broad-spectrum noises. A Fourier-based speech enhancement algorithm performs well in enhancing the corrupted vowel signals, and this algorithm fails in enhancing the corrupted consonant signals.
    Experimental results show that the novel scheme performs well in detecting the C/V boundaries for a spontaneously spoken utterance.
    關聯: 2005 International Symposium on Communications
    显示于类别:[資訊傳播學系] 會議論文

    文件中的档案:

    档案 大小格式浏览次数
    index.html0KbHTML145检视/开启


    在ASIAIR中所有的数据项都受到原著作权保护.


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