A revolutionary feature of emerging media services over the Internet is their ability to account for human\r\nperception during service delivery processes, which surely increases their popularity and incomes. In such a\r\nsituation, it is necessary to understand the users� perception, what should obviously be done using standardized\r\nsubjective experiences. However, it is also important to develop artificial quality assessors that enable to\r\nautomatically quantify the perceived quality. This efficiently helps performing optimal network and service\r\nmanagement at the core and edges of the delivery systems. In our article, we explore the behavior rating of new\r\nemerging artificial speech quality assessors of VoIP calls subject to moderately bursty packet loss processes. The\r\nexamined Speech Quality Assessment (SQA) algorithms are able to estimate speech quality of live VoIP calls at runtime\r\nusing control information extracted from header content of received packets. They are especially designed to\r\nbe sensitive to packet loss burstiness. The performance evaluation study is performed using a dedicated set-up\r\nsoftware-based SQA framework. It offers a specialized packet killer and includes the implementation of four SQA\r\nalgorithms. A speech quality database, which covers a wide range of bursty packet loss conditions, has been\r\ncreated and then thoroughly analyzed. Our main findings are the following: (1) all examined automatic bursty-loss\r\naware speech quality assessors achieve a satisfactory correlation under upper (> 20%) and lower (< 10%) ranges of\r\npacket loss processes; (2) they exhibit a clear weakness to assess speech quality under a moderated packet loss\r\nprocess; (3) the accuracy of sequence-by-sequence basis of examined SQA algorithms should be addressed in\r\ndetail for further precision.
Loading....