{"title":"A Test Scheme Design of Chinese Speech Recognition System","authors":"Yanfei Liu","doi":"10.1109/AIAM57466.2022.00017","DOIUrl":null,"url":null,"abstract":"This paper analyzes the characteristics and classification of the current speech recognition system, the existing test scheme and the existing problems. On this basis, a test scheme is provided for voice detection speech recognition system. By establishing a voice sample library to store test samples, the storage of command words, the selection of combinations and the reproduction of test conditions are realized, and the utilization rate and efficiency of test samples are improved. Combined with the actual application environment of the speech recognition system, the test system has carried out the test environment classification test scheme, carried out the pure environment command word test and the interference environment fault tolerance test, respectively characterized the speech recognition system's ability to recognize itself and adapt to the environment, and directly output the test results. Through experimental verification, this scheme can improve the accuracy of the test results of the speech recognition ability test, and improve the horizontal comparability of the related sound detection systems.","PeriodicalId":439903,"journal":{"name":"2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AIAM57466.2022.00017","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
This paper analyzes the characteristics and classification of the current speech recognition system, the existing test scheme and the existing problems. On this basis, a test scheme is provided for voice detection speech recognition system. By establishing a voice sample library to store test samples, the storage of command words, the selection of combinations and the reproduction of test conditions are realized, and the utilization rate and efficiency of test samples are improved. Combined with the actual application environment of the speech recognition system, the test system has carried out the test environment classification test scheme, carried out the pure environment command word test and the interference environment fault tolerance test, respectively characterized the speech recognition system's ability to recognize itself and adapt to the environment, and directly output the test results. Through experimental verification, this scheme can improve the accuracy of the test results of the speech recognition ability test, and improve the horizontal comparability of the related sound detection systems.