{"title":"Development of a MOS estimation model for G.729 using listening-opinion tests with Thai speech referring to packet loss effects","authors":"Pongpisit Wuttidittachotti, Phisit Khaoduang, Therdpong Daengsi","doi":"10.1109/ISCAIE.2014.7010204","DOIUrl":null,"url":null,"abstract":"This paper presents a proposed mathematical model of VoIP quality estimation from G.729. This model is based on native Thai users. The subjective Mean Opinion Score (MOS) were obtained from listening-opinion tests with a total of 102 subjects that covered five conditions of packet loss effects (0%, 3%, 5%, 10% and 20%). The model was then created using a simple function in Microsoft Excel, before evaluating with the test set data obtained from four test conditions (0%, 4%, 8% and 12%) with 30 subjects. From the evaluated result, it has been found that the Mean Absolute Percent Error (MAPE) of the model is 16.29%. That means this model is accepted as a good model for MOS estimation from G.729 for Thai users, referring to packet loss effects (0-10% =excellent, whereas about 10-20% = good).","PeriodicalId":385258,"journal":{"name":"2014 IEEE Symposium on Computer Applications and Industrial Electronics (ISCAIE)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 IEEE Symposium on Computer Applications and Industrial Electronics (ISCAIE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISCAIE.2014.7010204","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
This paper presents a proposed mathematical model of VoIP quality estimation from G.729. This model is based on native Thai users. The subjective Mean Opinion Score (MOS) were obtained from listening-opinion tests with a total of 102 subjects that covered five conditions of packet loss effects (0%, 3%, 5%, 10% and 20%). The model was then created using a simple function in Microsoft Excel, before evaluating with the test set data obtained from four test conditions (0%, 4%, 8% and 12%) with 30 subjects. From the evaluated result, it has been found that the Mean Absolute Percent Error (MAPE) of the model is 16.29%. That means this model is accepted as a good model for MOS estimation from G.729 for Thai users, referring to packet loss effects (0-10% =excellent, whereas about 10-20% = good).