互動式語音導覽系統 ; An Interactive Speech Guidance System

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Electrical Engineering > Electronic Thesis & Dissertation > Item 987654321/44602

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/44602

Title:	互動式語音導覽系統;An Interactive Speech Guidance System
Authors:	林佑輯;You-ji Lin
Contributors:	電機工程研究所
Keywords:	語音活動偵測;關鍵詞萃取;語音導覽系統;speech guidance system;keyword spotting;voice activity detection
Date:	2010-06-19
Issue Date:	2010-12-09 13:50:15 (UTC+8)
Publisher:	國立中央大學
Abstract:	本論文主要是設計一個互動式語音導覽系統。我們模擬遊客在博物館中使用多媒體系統的情形，此系統所提供的服務包括地名、人物、產業及景點等的介紹，經由人機互動的問答方式提供友善的使用者介面，且採用語音合成來模擬人聲作為回應。以次音節單元的關鍵詞萃取辨識技術可提高系統的可換性與移植性，在端點偵測的研究中，我們加入語音前後段的門檻值限制，以提升偵測正確率。藉由關鍵詞字彙結構的相關性，將所有的關鍵詞予以分類成一階層式架構，不但能降低非相關性字彙的誤判，還可大幅的減少辨識時間，在本論文裡，我們以8男8女的語料，針對50個關鍵詞來做辨識率的測試，實驗結果得到95.7%的辨識率及平均辨識一個句子需要0.25秒的時間。This thesis deals with the design of an interactive speech guidance system for Dasi and Longtan. We use a hierarchical structure for keyword spotting to improve the recognition capability of the system. Through a series of questions and answers, a user-friendly interface is established. The developed speech guidance system provides interesting information for Dasi and Longtan, including the geographical names, some famous persons, industries, scenic spots and so on. In our experiments, over 800 utterances pronounced by 8 males and 8 females are used to test the system performance. In average 0.25 seconds is spent for identifying a keyword and a recognition rate of 95.7% is obtained for the developed speech guidance system.
Appears in Collections:	[Graduate Institute of Electrical Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	643	View/Open

社群 sharing

Loading...