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: Acoustic Feature Analysis and Discriminative Modeling of Filled Pauses
作者Authors: 顏國郎,CHUNG-HSIEN..等
上傳單位Department: 資訊工程系
上傳時間Date: 2009-12-1
上傳者Author: 顏國郎
審核單位Department: 資訊工程系
審核老師Teacher: 顏國郎
檔案類型Categories: 論文Thesis
關鍵詞Keyword: filled pause, disfluency, Guassian mixture model, speech recognition, Karhunen-Lo´eve transform,, linear discriminant analysis
摘要Abstract: Most automatic speech recognizers (ASRs) concentrate on read speech, which is different from spontaneous
speech with disfluencies. ASRs cannot deal with speech with a high rate of disfluencies such as filled pauses,
repetitions, lengthening, repairs, false starts and silence pauses. In this paper, we focus on the feature analysis
and modeling of the filled pauses “ah,” “ung,” “um,” “em,” and “hem” in spontaneous speech. Karhunen-Lo´eve
transform (KLT) and linear discriminant analysis (LDA) were adopted to select discriminant features for filled
pause detection. In order to suitably determine the number of discriminant features, Bartlett hypothesis testing was
adopted. Twenty-six features were selected using Bartlett hypothesis testing. Gaussian mixture models (GMMs),
trained with a gradient decent algorithm, were used to improve the filled pause detection performance. The experimental
results show that the filled pause detection rates using KLT and LDA were 84.4% and 86.8%, respectively.
A significant improvement was obtained in the filled pause detection rate using the discriminative GMM with KLT
and LDA. In addition, the LDA features outperformed the KLT features in the detection of filled pauses.

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
2009_12_0d268d49.pdf 300Kb pdf 573 150
文件中檔案:
 

開啟檔案Download
 
 
返回前一頁