{"title":"Natural Language Voice Control Interface for People with Special Needs and Disabilities","authors":"S. Kirillov, O. E. Shustikov, V. Dmitriev","doi":"10.1109/SUMMA48161.2019.8947472","DOIUrl":null,"url":null,"abstract":"Natural language interface has been developed to provide voice control, information support and training for people with special needs. The requirements for a natural language interface program for people with special needs are considered. Six basic modes of operation of natural language interface taking into account the needs of people with special needs are proposed. It is shown that the use of optimal weight function will ensure the construction of attribute system based on the consistent estimates of generalized power spectrum of a speech signal increasing overall recognition reliability by 10 … 12%.","PeriodicalId":163496,"journal":{"name":"2019 1st International Conference on Control Systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 1st International Conference on Control Systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SUMMA48161.2019.8947472","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
Natural language interface has been developed to provide voice control, information support and training for people with special needs. The requirements for a natural language interface program for people with special needs are considered. Six basic modes of operation of natural language interface taking into account the needs of people with special needs are proposed. It is shown that the use of optimal weight function will ensure the construction of attribute system based on the consistent estimates of generalized power spectrum of a speech signal increasing overall recognition reliability by 10 … 12%.