A New Approach of Speaking Rate Modeling for Mandarin Speech Prosody

CHUR > College of Humanities and Social Sciences > Language Center > Seminar papers > Item 987654321/26999

Please use this identifier to cite or link to this item: http://chur.chu.edu.tw/handle/987654321/26999

Title:	A New Approach of Speaking Rate Modeling for Mandarin Speech Prosody
Authors:	余秀敏 Yu, Hsiu-min
Contributors:	語言中心
Keywords:	與速;韻律模型的建立 speaking rate;prosody modeling
Date:	2012
Issue Date:	2014-06-26 23:18:24 (UTC+8)
Abstract:	本研究為漢語韻律模型提出考量語速的心取徑。本模型建立在將之前我們我研發之韻律標注及方法的基礎上，將語速視為連續獨立之變數，好讓韻律─聲學特徵以及一些韻律模型之參數能依賴語速這個變數並計算語速對韻律的影響。我們以一位女性發音人快速、正常速、中速、慢速等四個不同語速的語料庫，建立了一個具有階層性、並因語速而變的韻律模型。我們分析語速對模型參數的影響與我們之前的理解十分一致，因此我們提出的新取徑是個能將語速進行系統性和有效的量化方式。 A new approach of Mandarin-speech prosody modeling to consider the effects of speaking rate is proposed. The approach is a modification of our previous prosody labeling and modeling method to take speaking rate as a continuous independent variable and let
Appears in Collections:	[Language Center] Seminar papers

Files in This Item:

File	Description	Size	Format
s_l_0003.pdf		29Kb	Adobe PDF	450	View/Open