TAILIEUCHUNG - Báo cáo khoa học: "A Dialogue System with Contextually Appropriate Spoken Output Intonation"

We demonstrate the production of spoken output with contextually appropriate intonation in the information-state based dialogue system GoDiS. We exploit the context representation in the information state to determine the information structure of system utterances, which we use to control the intonation of synthesized spoken output. | A Dialogue System with Contextually Appropriate Spoken Output Intonation Ivana Kruijff-Korbayova1 Elena Karagjosova1 University of the Saarland Germany korbay kepa elka @ Kepa J. Rodríguez1 Stina Ericsson2 2University of Gothenburg Sweden stinae@ Abstract We demonstrate the production of spoken output with contextually appropriate intonation in the information-state based dialogue system GoDiS. We exploit the context representation in the information state to determine the information structure of system utterances which we use to control the intonation of synthesized spoken output. 1 Introduction Producing spoken output with contextually appropriate intonation is one of the challenges for flexible dialogue systems with dynamically constructed output and synthesized speech. It is a well known fact that intonation reflects the relation of an utterance to the context and that contextually inappropriate intonation may have negative effect on intelligibility or lead to confusion. We demonstrate improvements of contextual appropriateness of English and German intonation in the GoDiS system. Intonation is controlled by information structure which is determined from the context representation in the information state of the system using the information-state update approach to dialogue. This note is structured as follows. In 2 we give an overview of GoDiS and its information-state update approach. In 3 we introduce the information structure partitioning we employ and the rules we use to determine it from the information state. In 4 we describe the generation of spoken output with contextually varied intonation in GoDiS using the Festival and Mary text-to-speech synthesis systems. In 5 we summarize and indicate our further research plans. 2 GoDiS GoDiS Gothenburg Dialogue System is an experimental dialogue system implemented using the TrindiKit a toolkit for implementing dialogue move engines and dialogue systems based on the information-state .

• Báo cáo khoa học
• A Dialogue System
• Contextually Appropriate
• Spoken Output Intonation
• scientific reports
• model language
• process natural language
• An ISU Dialogue System Exhibiting Reinforcement Learning
• Dialogue Policies
• Generic Slot filling
• TALK In car System
• Semantic Information and Derivation Rules
• Robust Dialogue Act Detection
• a Spoken Dialogue System
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Combining POMDPs trained
• User Simulations and Rule based Dialogue Management
• Spoken Dialogue System
• xử lý ngôn ngữ tự nhiên
• Chat oriented Dialogue System based
• the Vector Space Model
• Rafael E
• Banchs
• Resumption strategies
• in vehicle dialogue system
• Jessica Villing
• Comparing Objective
• Subjective Measures of Usability
• Human Robot Dialogue System
• A Multimodal
• Multilingual Dialogue System
• the Home Domain
• mô hình ngôn ngữ
• Multimodal Generation
• COMIC Dialogue System
• Mary Ellen Foster and Michael White
• Data Driven Strategies
• an Automated Dialogue System
• Hilda HARDY
• Evaluating a Trainable
• Sentence Planner
• The CommandTalk Spoken
• Dialogue System
• Amanda Stent
• John Dowding
• A Robust System
• Natural Spoken Dialogue
• James F
• Allen
• Bradford W
• Miller
• Eric K
• Ringger
• Teresa Sikorski
• EXPERIENCES WITH AN ON LINE
• TRANSLATING DIALOGUE SYSTEM
• Seiji MHKE
• Koichi HASEBE
• Evaluating language understanding accuracy
• respect to objective outcomes
• A Statistical Spoken Dialogue System
• Complex User Goals
• Value Directed Compression
• Producing Contextually
• Appropriate Intonation
• Information State Based Dialogue System
• Dialogue Processing
• CALL System
• Workshop
• A Descriptive Framework
• Translating Speakers Meaning Towards a Dialogue Translation System
• Japanese and English
• Dialogue Systems
• SDSs
• Data Pre Analysis Multidimensional
• System Specification
• Design
• Evaluation
• Business system development
• Information systems
• Information systems analysis
• Application software
• Systems development
• Dialogue design
• Web page layout design
• Advanced In Vehicle
• Spoken Dialog Corpus
• Robust Dialog Management
• Correcting Code
• Robust Speech Recognition
• báo cáo hóa học
• công trình nghiên cứu về hóa học
• tài liệu về hóa học
• cách trình bày báo cáo