跳到主要內容

臺灣博碩士論文加值系統

(18.204.56.185) 您好!臺灣時間:2022/08/14 02:35
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:葉禮宗
研究生(外文):Li-Tzong Yeh
論文名稱:對話介面代理人-以推薦旅遊行程為例
論文名稱(外文):Dialogue Interface Agent-with a Recommending Trip Plan Travel Agent
指導教授:蘇豐文蘇豐文引用關係
指導教授(外文):Von-Wun Soo
學位類別:碩士
校院名稱:國立清華大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:中文
論文頁數:53
中文關鍵詞:語音對話介面代理人本體論知識語音辨識旅遊代理人
外文關鍵詞:Speech DialogueInterfaceAgentOntologySpeech RecognitionTravel Agent
相關次數:
  • 被引用被引用:10
  • 點閱點閱:1798
  • 評分評分:
  • 下載下載:519
  • 收藏至我的研究室書目清單書目收藏:9
我們認為最直覺的介面使用方法就是語音對話,於是我們設計了一個對話介面代理人,作為服務系統的介面,將服務功能與介面功能分離獨立,導引使用者設定、使用。在本論文中,對話介面代理人與推薦旅遊行程代理人共同合作互動提供服務。我們利用了以隱藏式馬可夫模型 (Hidden Markov Models) 技術實作的中文語音辨識引擎、IBM ViaVoice 中文文字轉語音 (Text-to_Speech) 引擎、微軟代理人 (Microsoft Agent)來作支援,提供電腦系統中文語音說與聽的能力來對話,以及有直覺性視覺效果的動畫。由於語音的辨識有其極限,總是會有辨識錯誤的時候,加上背景待辨識字詞的數量影響辨識時間甚大,我們提出以控制背景待辨識字詞集的方式,配合對話策略,辨識錯誤的時候,系統能夠持續與使用者對話,找出使用者想要輸入的字詞。本論文最感興趣的是對於一般文字字詞辨識錯誤的處理。我們解決了語音辨識引擎有背景字詞數目上限的問題,對於觀察特徵少的字詞集、使用者記錯字的字詞、同音異字字詞的分別,我們都能對話找出答案字詞。語音輸入的字詞是否真的存在我們的背景字詞集中,我們也可以知道。此外有對話歷史功能,允許使用者從之前未完成的序列繼續對話。對系統領域不熟悉的使用者,可以請求系統支援導引查詢資訊。
Speech dialogue is the most intuitive presentation of computer system user interface. We propose a dialogue interface agent for the user interface agent of service agent systems. It separates the interface from service systems. The dialogue interface agent guides users to use service systems. In this thesis, the dialogue interface agent interacts with travel agent system to serve users. It employs the Chinese speech recognition engine supported by Hidden Markov Models technology and IBM ViaVoice Chinese Text-to-Speech engine and Microsoft Agent altogether providing the speaking and hearing abilities and furthermore the visual animations. Result from the limitation of speech recognition engine, sometimes, it may get wrong hearing; besides, the recognition response time is enormously correlated with the amount of words to be recognized. By controlling the words set to be recognized applying dialogue strategies, as wrong speech recognition happens it can dialogue with users continuously and smoothly to percept user’s demanded word. We are in particularly interested in the process of wrong speech recognition of general words. We solve the problem that there is limitation in the amount of words to be recognized. For the condition that word sets have few observation characters and the condition that users mistake speaking and the case to distinguish between homophones, we can still find out the correct users’ demanded words. We can also realize whether a word is in the valid word set. Moreover, by dialogue history records, users can restart their not-yet set-up dialogue items. For those who are not familiar with the domain knowledge of service systems, they could invite the dialogue interface agent to guide them to query related information.
內容 1
第一章 前言 3
1.1 背景與動機 3
1.2 問題描述 3
1.3 相關工作 4
1.3.1 推薦旅遊行程代理人系統 4
1.3.2 語音辨識引擎 - 使用隱藏式馬可夫模型 5
1.3.3 微軟代理人 7
1.3.4 對話系統 8
1.3.5 介面代理人系統 10
1.4 論文架構 10
第二章 系統概述 12
2.1 旅遊代理人 13
2.1.1 系統宏觀 14
2.1.2 互動流程 14
2.2 對話介面代理人 16
2.2.1 系統宏觀 16
2.2.2 單元簡述 17
2.3對話介面 17
第三章 對話代理人後端 20
3.1 服務管理器 20
3.1.1 通訊協定 20
3.1.2 工作內容 22
3.2 知識庫 22
3.3 內文模式 25
3.3.1 對話樣本 25
3.3.2 內文效能 26
第四章 對話代理人前端 27
4.1 感知 27
4.1.1 一般字詞感知 28
4.1.2 數目字詞感知 34
4.1.3 時間字詞感知 34
4.2 反應 35
4.2.1 語音輸出 35
4.2.2 動畫 35
4.3 對話 37
第五章 實作與結果 41
5.1 實作 41
5.2 結果 41
Scenario:三種類型對話的整合 42
Scenario:確知字詞例外 43
Scenario:數目廣大及觀察特徵少的字詞集 44
Scenario:語音混淆不清 45
Scenario:資料庫再過濾 46
Scenario:資訊導引 46
Scenario:對話歷史 47
第六章 結論與未來工作 49
參考文獻 51
[1] Von-Wun Soo and Shu-How Liang, Recommending a Trip Plan by Negotiation With a Travel Agent, Artificial Intelligence Lab CS Dept. National Tsing Hua University, Taiwan, 2001.
[2] HTK, Hidden Markov Model Toolkit V3.1, Speech Vision and Robotics Group of the Cambridge University Engineering Department, 2002. Page(s):96-117
[3] Rabiner L.R. and Juang B.H., An Introduction to Hidden Markov Models, IEEE ASSP Magazine, 1986. pp.4-16.
[4] Rebecca McKay and Ben Ryan, Microsoft Agent Software Development Kit, Microsoft Press, 1999.
[5] Jyh-Shing Roger Jang and Shiuan-Sung Lin, Optimisation of Viterbi Beam Search in Speech Recognition, Multimedia Information Retrieval Lab CS Dept. National Tsing Hua University, Taiwan, 2002.
[6] Von-Wun Soo and Hai-Long Cheng, Conducting the Disambiguation Dialogues Between Software Agent Sellers and Human Buyers, Artificial Intelligence Lab CS Dept. National Tsing Hua University, Taiwan, 2001.
[7] Andreas Kellner, Bernd Rueber, and Hauke Schramm, Strategies for Name Recognition in Automatic Directory Assistance Systems, Interactive Voice Technology for Telecommunications Applications, IVTTA ''98. Proceedings. 1998 IEEE 4th Workshop , Page(s): 21 -26
[8] Zue, V.; Seneff, S.; Glass, J.R.; Polifroni, J.; Pao, C.; Hazen, T.J. and Hetherington, L, JUPlTER: A Telephone-based Conversational Interface for Weather Information, Speech and Audio Processing, IEEE Transactions on, Volume: 8 Issue: 1, Jan. 2000. Page(s): 85 -96
[9] Lamel, L; Rosset, S.; Gauvain, J.L.; Bennacef, S.; Garnier-Rizet, M. and Prouts, B., The LIMSI ARISE System [Rail Travel Information System], Interactive Voice Technology for Telecommunications Applications, IVTTA’98. Proceedings. IEEE 4th Workshop, Page(s): 209 -214
[10] Seneff, S. and Polifroni, J, A New Restaurant Guide Conversational System: Issues in Rapid Prototyping for Specialized Domains, Spoken Language, ICSLP 96, Proceedings, Fourth International Conference on, Volume: 2, 1996. Page(s): 665 -668 vol.2
[11] Timothy Bickmore and Justine Cassell, How About This Weather? Social Dialogue with Embodied Conversational Agents, Proceedings of the AAAI Fall Symposium on Socially Intelligent Agents, 2000. Page(s): 4-9
[12] Timothy Bickmore and Justine Cassell, Small Talk and Conversational Storytelling In Embodied Conversational Interface Agents, Proceedings of the AAAI Fall Symposium on Narrative Intelligence, 1999. Page(s): 87-93
[13] Noriko Suzuki, Kazuo Ishii and Michio Okada, Talking Eye: Autonomous Creature as Accomplice for Human, Computer Human Interaction, Proceedings. 3rd Asia Pacific , 1998. Page(s): 409-414
[14] Leila Amgoud, Nicolas Maudet, and Simon Parson, Modelling Dialogues Using Argumentation, Proceedings of the 4th International Conference on Multi-Agent Systems, Boston, 2000. Page(s):31-38
[15] Werner Kiebling, Stefan Fischer, Stefan Holland and Thorsten Ehm, Design and Implementation of COSIMA - A Smart and Speaking E-Sales Assistant, Advanced Issues of E-Commerce and Web-Based Information Systems, WECWIS 2001, Third International Workshop on. , 2001. Page(s):21-30
[16] Yasmine Arafa and Abe Mamsani, Face-to-Face Interaction with An Electronic Personal Sales Assistant, Systems, Man, and Cybernetics, 2000 IEEE International Conference on , Volume: 2 . Page(s):792-797
[17] Takashi Nishiyama, Shuji Murakami, Ryoji Nakajima, Kazuya Sawada and Osamu Katai, The Application of Interface Agent to A Health Care System, Systems, Man, and Cybernetics, IEEE SMC ''99 Conference Proceedings. IEEE International Conference on , Volume: 1 , Page(s):750-755
[18] Stuart Russell and Peter Norvig, Artificial Intelligence — A Modern Approach, Prentice Hall, 1995. Page(s):226-247
[19] Bellifemine F., Poggi, A. and Rimassa, G., JADE — A FIPA-compliant Agent Framework, in Proceedings of PAAM''99, London, April 1999.
[20] FIPA Org, http://www.fipa.org/
[21] FIPA Interaction Protocol Library Specification.
See http://www.fipa.org/specs/fipa00025/XC00025D.pdf
[22] FIPA Agent Communication Language Specification.
See http://www.fipa.org/specs/fipa00003/OC000003.pdf
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊