An Utterance Prediction Method Based on the Topic Transition Model

スポンサーリンク

概要

• 論文の詳細を見る

• This paper describes a method for predicting the user's next utterances in spoken dialog based on the topic transition model, named TPN. Some templates are prepared for each utterance pair pattern modeled by SR-plan. They are represented in terms of five kinds or topic-independent constituents in sentences. The topic of an utterance is predicted based on the TPN model and it instantiates the templates. The language processing unit analyzes the speech recognition result using the templates. An experiment shows that the introduction of the TPN model improves the performance of utterance recognition and it drastically reduces the search space of candidates in the input bunsetsu lattice.

• 社団法人電子情報通信学会の論文
• 1995-06-25

著者

• Mizoguchi Riichiro

  Institute of Scientific and Industrial Research, Osaka University

• Hiramatsu Takashi

  Institute Of Scientific And Industrial Research Osaka University

• Hiramatsu Takashi

  Muroto Mfg. Co. Ltd.

• Yamashita Yoichi

  Institute of Scientific and Industrial Research, Osaka University

• Yamashita Y

  Institute Of Scientific And Industrial Research Osaka University

• Yamashita Y

  Department Of Computer Science Ritsumeikan University

• Kakusho Osamu

  Faculty of Science and Technology, Ryukoku University

• Kakusho O

  Hyogo Univ. Kakogawa‐shi Jpn

• Mizoguchi R

  Osaka Univ. Ibaraki Jpn

• Mizoguchi Riichiro

  Institute Of Scientific And Industrial Research Osaka University

関連論文

• An Inductive Student Modeling Method which Deals with Student Contradictions (Special Issue on Intelligent CAI and Hypermedia)
• Design of an ITS for Strategic Knowledge in Proving Logical Formulas (Special Issue on Intelligent CAI and Hypermedia)
• MASCOTS II: A Dialog Manager in General Interface for Speech Input and Output (Special Issue on Speech and Discourse Processing in Dialogue Systems)
• Extraction of important sentences for speech summarization based on an F_0 model
• Dielectric Properties of Fine-Grained BaTiO_3 Ceramics Doped with CaO
• Tree-Based Approaches to Automatic Generation of Speech Synthesis Rules for Prosodic Parameters : Special lssue on Speech Synthesis: Current Technologies and Equipment
• Interactive Synthesis of Conceptual Schema Based on Queries : Towards an Expert System of Relational Database Design
• An Utterance Prediction Method Based on the Topic Transition Model
• Designing High-Quality Approximation Algorithms for Combinatorial Optimization Problems(Special Issue on Algorithm Engineering : Surveys)

スポンサーリンク