Single-ended parametric voicing-aware models for live assessment of packetized VoIP conversations

Abstract

The perceptual quality of VoIP conversations depends tightly on the pattern of packet losses, i.e., the distribution and duration of packet loss runs. The wider (resp. smaller) the inter-loss gap (resp. loss gap) duration, the lower is the quality degradation. Moreover, a set of speech sequences impaired using an identical packet loss pattern results in a different degree of perceptual quality degradation because dropped voice packets have unequal impact on the perceived quality. Therefore, we consider the voicing feature of speech wave included in lost packets in addition to packet loss pattern to estimate speech quality scores. We distinguish between voiced, unvoiced, and silence packets. This enables to achieve better correlation and accuracy between human-based subjective and machine-calculated objective scores. This paper proposes novel no-reference parametric speech quality estimate models which account for the voicing feature of signal wave included in missing packets. Precisely, we develop separate speech quality estimate models, which capture the perceptual effect of removed voiced or unvoiced packets, using elaborated simple and multiple regression analyses. A new speech quality estimate model, which mixes voiced and unvoiced quality scores to compute the overall speech quality score at the end of an assessment interval, is developed following a rigorous multiple linear regression analysis. The input parameters of proposed voicingaware speech quality estimate models, namely Packet Loss Ratio (PLR) and Effective Burstiness Probability (EBP), are extracted based on a novel Markov model of voicing-aware packet loss which captures properly the feature of packet loss process as well as the voicing property of speech wave included in lost packets. The conceived voicing-aware packet loss model is calibrated at run time using an efficient packet loss event driven algorithm. The performance evaluation study shows that our voicing-aware speech quality estimate models outperform voicing-unaware speech quality estimate models, especially in terms of accuracy over a wide range 2 of conditions. Moreover, it validates the accuracy of the developed parametric no-reference speech quality models. In fact, we found that predicted scores using our speech quality models achieve an excellent correlation with measured scores (>0.95) and a small mean absolute deviation (<0.25) for ITU-T G.729 and G.711 speech CODECs.

Quality assessment and usage behavior of a mobile voice-over-IP service

“…For VoIP calls, packet losses and the pattern of the packet losses, i.e., the distribution and duration of packet loss runs, has a significant influence on the perceptual quality of the conversation [3]. The wider the inter-loss gap duration, the lower is the quality degradation [18]. But also the jitter, i.e., the inter-packet delay encountered as packets are transmitted through the network from sender to receiver, has a significant influence on the quality of calls [4].…”

Advanced solution of SIP communication server with a new approach to management

“…The security module is based on SNORT, SNORTSam and IPtables [8,9]. The monitoring module exploits a tshark package and our developed tool which provides information about the quality of a particular speech [10,11]. The Zabbix agent is used to report basic states of the entire system.…”

Using Rater and System Metadata to Explain Variance in the VoiceMOS Challenge 2022 Dataset

“…Alongside listener metadata, it may be valuable to consider using metadata related to the signal. Previous research has used aspects of network transmission, such as packet loss rate [19,20]. Synthetic data has additional properties that can be used as metadata that do not exist in natural data, such as the synthesis system description.…”