尚未登入 請由此登入
 
 
 










知識分享平台Eshare檢視資訊View
返回前一頁Back
      [檢舉]

標題Title: Classification of place of articulation in unvoiced stops with spectro-temporal surface modeling
作者Authors: 郭岳峯
上傳單位Department: 電機工程系
上傳時間Date: 2013-6-8
上傳者Author: 郭岳峯
審核單位Department: 電機工程系
審核老師Teacher: 楊弘吉
檔案類型Categories: 研究生論文報告Thesis
關鍵詞Keyword: Unvoiced stops are rapidly varying sounds with acoustic cues to place identity linked to the temporal dynamics.
摘要Abstract: Unvoiced stops are rapidly varying sounds with acoustic cues to place identity linked to the temporal dynamics. Neurophysiological studies have indicated the importance of joint spectro-temporal processing in the human perception of stops. In this study, two distinct approaches to modeling the spectro-temporal envelope of unvoiced stop phone segments are investigated with a view to obtaining a low- dimensional feature vector for automatic place classification. Classification accuracies on the TIMIT database and a Marathi words dataset show the overall superiority of classifier combination of polynomial surface coefficients and 2D-DCT.

檔案名稱
FileName
檔案大小
Size
檔案格式
Format
瀏覽次數
Browses
下載次數
Downloads
2013_6_a67de5e1.pptx 527Kb pptx 90 15
文件中檔案:
 

開啟檔案Download
 
 
返回前一頁