Y. Seliverstov, Andrey A. Komissarov, Dmitry A. Tsyrkov, Stanislav S. Torsionov, Alina A. Lesovodskaya, Artur V. Podtikhov
{"title":"Development of an Intelligent Speech Analysis System","authors":"Y. Seliverstov, Andrey A. Komissarov, Dmitry A. Tsyrkov, Stanislav S. Torsionov, Alina A. Lesovodskaya, Artur V. Podtikhov","doi":"10.1109/scm55405.2022.9794875","DOIUrl":null,"url":null,"abstract":"The concept of oral speech is formalized, various methods and approaches for the quantitative analysis of oral speech are identified and studied, a methodology for analyzing oral speech is developed based on discursive indicators, criteria for connectedness, fluency, clarity, intelligibility, tonality, emotionality of speech, readability of the meaningful part of speech, models of multiclass classifiers are built. in terms of sectoral and emotional differentiation of texts, the architecture of the oral speech analysis service is being developed, based on the developed methodology, models of multi-parameter analysis of oral speech are being developed and implemented in software, a visual interface is being developed that clearly demonstrates the results of automatic analysis of oral speech.","PeriodicalId":162457,"journal":{"name":"2022 XXV International Conference on Soft Computing and Measurements (SCM)","volume":"232 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 XXV International Conference on Soft Computing and Measurements (SCM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/scm55405.2022.9794875","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
The concept of oral speech is formalized, various methods and approaches for the quantitative analysis of oral speech are identified and studied, a methodology for analyzing oral speech is developed based on discursive indicators, criteria for connectedness, fluency, clarity, intelligibility, tonality, emotionality of speech, readability of the meaningful part of speech, models of multiclass classifiers are built. in terms of sectoral and emotional differentiation of texts, the architecture of the oral speech analysis service is being developed, based on the developed methodology, models of multi-parameter analysis of oral speech are being developed and implemented in software, a visual interface is being developed that clearly demonstrates the results of automatic analysis of oral speech.