Voicing-aware parametric speech quality models over VoIP networks

Jelassi, Sofiene; Youssef, Habib; Hoene, Christian; Pujolle, Guy

doi:10.1109/giis.2009.5307097

Cited by 11 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jelassi et al [32] extended the conventional parametric speech quality estimation models by considering the voicing feature of lost packets. This model builds a voicing-aware speech quality model that allows to accurately quantifying the effect of lost packets according to their voicing property.…”

Section: Hybrid Algorithmsmentioning

confidence: 99%

“…GMM are used, again, to generate an artificial reference model that is compared with the transmitted speech signal. On the other hand, a parametrical analysis similar to the previous one [32] is performed, evaluating the VoIP header. Consequently, this model inherits the limitations discussed above, related to the relevance of ignored impairments such as delay or jitter.…”

Section: Hybrid Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Revisiting VoIP QoE assessment methods: are they suitable for VoLTE?

Sánchez-Iborra

Cano

García-Haro

2016

NPA

View full text Add to dashboard Cite

Voice over LTE (VoLTE) emerges as the basis for voice services in future cellular networks. At the same time, Quality of user Experience (QoE) assessment methods have notably evolved in the last years, especially for Voice over IP (VoIP) services. The question that rises is, are these models ready to be used for VoLTE? In this paper, we contribute to answer this question by: (i) providing a high level exploration of current objective non-intrusive models for Voice over IP (VoIP) QoE evaluation, (ii) highlighting the review of works aiming to improve the standardized E-model (ITU-T Rec. G.107 (06/2015)) and the examination of non-standardized solutions proposed by the research community, and (iii) bringing forth the challenges identified for the completion of a successful QoE evaluation approach according to modern VoIP services such as VoLTE.

show abstract

Section: Hybrid Algorithmsmentioning

confidence: 99%

Section: Hybrid Algorithmsmentioning

confidence: 99%

Revisiting VoIP QoE assessment methods: are they suitable for VoLTE?

Sánchez-Iborra

Cano

García-Haro

2016

NPA

View full text Add to dashboard Cite

show abstract

“…As such, there is no subtle characterization and specification of the burstiness of the packet loss processes. This could lead to a wrong judgment of perceived quality because it has been subjectively observed that two distinct bursty packet loss patterns with identical PLR may lead to an obvious difference in the perceived quality [7]. Moreover, the rapidity of the exponential decay/growing is hold static independently of the duration of preceding Good or Bad state and the magnitude variation of previous and current packet loss ratios.…”

Section: Vqmon: Voice Quality Monitoringmentioning

confidence: 99%

A study of artificial speech quality assessors of VoIP calls subject to limited bursty packet losses

Jelassi

Rubino

2011

J Image Video Proc.

Self Cite

View full text Add to dashboard Cite

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

show abstract

“…These methodologies, so-called generate an artificial reference model that is compared with the transmitted speech signal. On the other hand, a parametrical analysis similar to previous[98] is performed, evaluating the VoIP header. Consequently, this model inherits the limitations discussed above, related to the relevance of ignored impairments such as measure the difference between the received and the reference speech signals.…”

mentioning

confidence: 99%

Contribution to quality of user experience provision over wireless networks

Iborra¹,

Jesús²

View full text Add to dashboard Cite

The widespread expansion of wireless networks has brought new attractive possibilities to end users. In addition to the mobility capabilities provided by unwired devices, it is worth remarking the easy configuration process that a user has to follow to gain connectivity through a wireless network. Furthermore, the increasing bandwidth provided by the IEEE 802.11 family has made possible accessing to high-demanding services such as multimedia communications. Multimedia traffic has unique characteristics that make it greatly vulnerable against network impairments, such as packet losses, delay, or jitter. Voice over IP (VoIP) communications, video-conference, video-streaming, etc., are examples of these high-demanding services that need to meet very strict requirements in order to be served with acceptable levels of quality. Accomplishing these tough requirements will become extremely important during the next years, taking into account that consumer video traffic will be the predominant traffic in the Internet during the next years. In wired systems, these requirements are achieved by using Quality of Service (QoS) techniques, such as Differentiated Services (DiffServ), traffic engineering, etc. However, employing these methodologies in wireless networks is not that simple as many other factors impact on the quality of the provided service, e.g., fading, interferences, etc. Focusing on the IEEE 802.11g standard, which is the most extended technology for Wireless Local Area Networks (WLANs), it defines two different architecture schemes. On one hand, the infrastructure mode consists of a central point, which manages the network, assuming network controlling tasks such as IP assignment, routing, accessing security, etc. The rest of the nodes composing the network act as hosts, i.e., they send and receive traffic through the central point. On the other hand, the IEEE 802.11 ad-hoc configuration mode is less extended than the infrastructure one. Under this scheme, there is not a central point in the network, but all the nodes composing the network assume both host and router roles, which permits the quick deployment of a network without a pre-existent infrastructure. This type of networks, so called Mobile Ad-hoc NETworks (MANETs), presents interesting characteristics for situations when the fast deployment of a communication system is needed, e.g., tactics networks, disaster events, or temporary networks. The benefits provided by MANETs are varied, including high mobility possibilities provided to the nodes, network Contribution to Quality of user Experience Provision over Wireless Networks II 5.

show abstract

Voicing-aware parametric speech quality models over VoIP networks

Cited by 11 publications

References 9 publications

Revisiting VoIP QoE assessment methods: are they suitable for VoLTE?

Revisiting VoIP QoE assessment methods: are they suitable for VoLTE?

A study of artificial speech quality assessors of VoIP calls subject to limited bursty packet losses

Contribution to quality of user experience provision over wireless networks

Contact Info

Product

Resources

About