Frequency-domain adaptive algorithm for network echo cancellation in VoIP
EURASIP Journal on Audio, Speech, and Music Processing - Intelligent Audio, Speech, and Music Processing Applications
A neural network based model for VoIP speech quality prediction
Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human
The memory effect and its implications on web QoE modeling
Proceedings of the 23rd International Teletraffic Congress
Modeling QoS parameters of VoIP traffic with multifractal and Markov models
ICA3PP'11 Proceedings of the 11th international conference on Algorithms and architectures for parallel processing - Volume Part II
Real-time quality assessment for voice over IP
Concurrency and Computation: Practice & Experience
From packets to people: quality of experience as a new measurement challenge
DataTraffic Monitoring and Analysis
Hi-index | 0.00 |
A speech-quality-oriented classification of packet loss distributions is proposed according to both the short- and long-term loss behavior. While the short-term behavior (microscopic loss behavior) relates to the effect of packet loss on the coder and packet loss concealment performance, the long-term loss behavior (macroscopic loss behavior) is defined so that it reflects the loss behavior that ultimately leads to speech quality that perceptively changes over time. Based on this classification, different parametric (objective) modeling approaches for predicting speech quality are discussed. To this aim, a packet loss averaging approach is presented for modeling speech quality under short-term loss. Starting from this model, two different ways for predicting speech quality under long-term-dependent packet loss are analyzed and compared to auditory (subjective) test results: quality prediction based on the averaging at packet trace level as provided, for example, by the E-model (2005), and the prediction based on the time-averaging of estimated instantaneous quality profiles, as suggested, for example, by L. Gros and N. Chateau (2001) (1998). From this comparison, the suitability of the different approaches for network planning are discussed, and their limitations in case of particular loss distributions are pointed out