Study of Multi-Modal Interface based on Simultaneous Understanding of Spoken Language

基于口语同步理解的多模态界面研究

• 批准号: 10480070
• 负责人: INAGAKI Yasuyoshi
• 金额: $ 4.67万
• 依托单位: Nagoya University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B)
• 财政年份: 1998
• 资助国家: 日本
• 起止时间: 1998 至 1999
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-10480070/
• 关键词: Multi-Modal Interface; Spoken Language Processing; Natural Language Processing; Incremental Interpretation of Natural Language; Simultaneous Understanding; Spontaneous Reply; Spoken Language Understanding; Spoken Dialogue; マルチモーダルインタフェース; 図形エディタ

The spoken dialog systems has been studied to help persons who cannot use hands or pointing devices and who do not familiar with keyboard nor computers. In this research project, we develop the system named Sync/Mail, which is a multi-modal drawing tool which incrementally understands speech and quickly responds for inputs. To implement the system, we investigate following topics.(1) Incremental Interpretation of Spoken LanguageConventional natural language processing systems manage natural language input by sentence-by-sentence basis process. Our incremental system processes the input by word-by-word basis. This method enables the spontaneous reply of input.(2) Incremental Continuous Speech Recognition(3) Method of Integration for Multi-Domain SystemsTo build the unified system for multi-domain task, it is required the method to integrate the several single-domain dialogue system into the one unified system. We proposed an extensible and scalable architecture for the multi-domain, multi-modal conversational systems.

语音对话系统的研究是为了帮助那些不能使用手或指点设备以及不熟悉键盘或计算机的人。在这个研究项目中，我们开发了名为 Sync/Mail 的系统，这是一种多模式绘图工具，可以逐步理解语音并快速响应输入。为了实现该系统，我们研究了以下主题。(1)口语的增量解释传统的自然语言处理系统通过逐句的基础过程来管理自然语言输入。我们的增量系统逐字处理输入。该方法可以实现输入的自发回复。（2）增量连续语音识别（3）多域系统集成方法要构建多域任务的统一系统，需要集成多个单域对话的方法系统成为一个统一的系统。我们为多领域、多模式对话系统提出了一种可扩展和可扩展的架构。

项目成果

加藤芳秀: "確率文脈自由文法を用いた漸進的構文解析における出力タイミング決定手法"情報処理学会第59回全国大会講演論文集. 4. 120-121 (1999)

Yoshihide Kato：“使用概率上下文无关语法的渐进解析中的输出时序确定方法”第 59 届日本信息处理学会全国会议论文集。4. 120-121 (1999)。

Nobuo Kawaguchi, Shigeki Matsubara, Katsuhiko Toyama and Yasuyoshi Inagaki: "An Architechture for Multi-Domain Spoken Dialog Systems"Proceedings of the 5th Natural Language Processing Pacific Rim Symposium (NL-PRS'99). 463-466 (1999)

Nobuo Kawaguchi、Shigeki Matsubara、Katsuhiko Toyama 和 Yasuyoshi Inagaki：“多域口语对话系统的架构”第五届环太平洋自然语言处理研讨会 (NL-PRS99) 论文集。

Nobuo Kawaguchi: "An Architecture for Multi-Domain Spoken Dialog Systems"Proceedings of the NLPRS '99. 463-466 (1999)

Nobuo Kawaguchi：“多域语音对话系统的架构”NLPRS 99 论文集。

Shigeki Matsubara, Hiroshi Ogawa, Katsuhiko Toyama and Yasuyoshi Inagaki: "Incremental Spoken Language Translation based on A Normal-Form Conversionof CFG"Proceedings of the 5th Natural Language Processing Pacific Rim Symposium (NL-PRS'99). 515-518 (1999)

Shigeki Matsubara、Hiroshi Okawa、Katsuhiko Toyama 和 Yasuyoshi Inagaki：“基于 CFG 范式转换的增量口语翻译”第五届环太平洋自然语言处理研讨会 (NL-PRS99) 论文集。

Muhtar Mahsut: "A Method of Word Selection in Japanese-Uighur Machine Translation using Latent Semantic Analysis"Proceedings of the NLPRS '99. 459-462 (1999)

Muhtar Mahsut：“使用潜在语义分析的日文-维吾尔文机器翻译中的词选择方法”NLPRS 99 论文集。