A New Application-Aware No-Reference Quality Assessment Method for IP Voice Services

Abstract The increasing number of Voice over LTE deployments and IP-based voice services raise the demand for their user-centric service quality monitoring. This domain’s leading challenge is measuring user experience reliably without performing subjective assessments or applying standard full-reference objective models. While former time- resource-consuming primarily executed ad-hoc, latter depends upon a reference source processes payload that may offend privacy. paper presents packet-level measurement method (introducing novel metric set) to objectively assess network online. It accomplished inspecting needing sample. proposal has three contributions: (i) our focuses on timeliness media traffic. introduces new performance metrics describe measure service’s time-domain behavior from application viewpoint. (ii) Based proposed metrics, we also present no-reference Quality Experience (QoE) estimation model. (iii) Additionally, propose identify pace speech (slow dynamic) as long activity detection (VAD) between endpoints. identification supports introduced model estimate perceived with higher accuracy. validated against called AQuA, using real VoIP traffic (originated in assorted samples) controlled transmission scenarios.