VoIP users’ Quality of Experience (QoE)Evaluation

Please enable javascript in your browser.

Hesam Mohseni, Abdorreza | 2022

36 Viewed

Type of Document: Ph.D. Dissertation
Language: English
Document No: 56744 (52)
University: Sharif University of Technology, International Campus, Kish Island
Department: Science and Engineering
Advisor(s): Jahangir, Amir Hossein
Abstract:
Quality of Experience (QoE) indicates the overall quality of one service such as Voice over IP (VoIP) from users' point of view by considering several systems, human, and contextual factors. QoE measurement and prediction are more challenging than Quality of Service (QoS) which is only related to network parameters. There exist various objective and subjective methods for QoE prediction. This research investigates various features affecting QoE by proposing a comprehensive subjective evaluation by employing a large number of users. We show that many unconsidered factors including speaker specifications and signal properties, such as signal-to-noise ratio (SNR), can affect QoE so that the SNR is a more significant factor in QoE than the packet loss rate, which is the most important QoS parameter. Our comprehensive analysis using Machine Learning (ML) techniques reveal that users' identity features such as the accent and gender of Persian people significantly influence QoE
Keywords:
Experience Quality ; Voice Over Internet Protocol (VOIP) ; Service Quality ; Signal to Noise Ratio ; Machine Learning ; Objective Test ; Subjective Test