{"title":"Construction of dialog database for development of spoken dialog breakdown detection methods","authors":"Kazuaki Kajinami, Ryota Nishimura, N. Kitaoka","doi":"10.1109/ICAICTA.2018.8541273","DOIUrl":null,"url":null,"abstract":"When talking with a spoken dialog system, the dialog often breaks down, and after that, the user cannot continue the dialog anymore because the system cannot know the breakdown. In order to recover from breakdown quickly, it is necessary to detect the dialog breakdown. Indeed some textbased dialog breakdown detector has been developed, there are no dialog breakdown detectors for spoken dialog systems. In addition, there was no dialog speech database to investigate dialog breakdown detectors for spoken dialog systems.So, we construct a dialog speech database which includes spoken dialog breakdowns. From the analysis of the database, we could observe many spoken dialog-specific breakdowns.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"212 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAICTA.2018.8541273","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
When talking with a spoken dialog system, the dialog often breaks down, and after that, the user cannot continue the dialog anymore because the system cannot know the breakdown. In order to recover from breakdown quickly, it is necessary to detect the dialog breakdown. Indeed some textbased dialog breakdown detector has been developed, there are no dialog breakdown detectors for spoken dialog systems. In addition, there was no dialog speech database to investigate dialog breakdown detectors for spoken dialog systems.So, we construct a dialog speech database which includes spoken dialog breakdowns. From the analysis of the database, we could observe many spoken dialog-specific breakdowns.