A non-intrusive method to assess voice quality over internet

Kapilan Radhakrishnan; Hadi Larijani; Tom Buggy

A non-intrusive method to assess voice quality over internet

Kapilan Radhakrishnan, Hadi Larijani, Tom Buggy

SCEBE School Office

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Voice over IP (VoIP) is an emerging service and has gained popularity in recent years. The most challenging task for a service provider is to provide and monitor better voice quality. The nature of quality of service (QoS) in VoIP networks is very variable and hence it is important to be able to measure the QoS offered by the system in real time with a low computational cost. In this paper, we discuss our new model to monitor and predict voice quality non-intrusively using Random Neural Networks (RNN). Our model is based on using network delay, delay variation (jitter), packet loss and different voice codecs as input.

Original language	English
Title of host publication	2010 International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS)
Publisher	IEEE
Pages	380-386
Number of pages	7
ISBN (Print)	9781565553408
Publication status	Published - 2010

Keywords

telecommunications
voice quality
internet
communication technology

Documents and Links

Fingerprint Dive into the research topics of 'A non-intrusive method to assess voice quality over internet'. Together they form a unique fingerprint.

Cite this

@inproceedings{6812111ba62e4e40ab425403a65602b8,

title = "A non-intrusive method to assess voice quality over internet",

abstract = "Voice over IP (VoIP) is an emerging service and has gained popularity in recent years. The most challenging task for a service provider is to provide and monitor better voice quality. The nature of quality of service (QoS) in VoIP networks is very variable and hence it is important to be able to measure the QoS offered by the system in real time with a low computational cost. In this paper, we discuss our new model to monitor and predict voice quality non-intrusively using Random Neural Networks (RNN). Our model is based on using network delay, delay variation (jitter), packet loss and different voice codecs as input. ",

keywords = "telecommunications, voice quality, internet, communication technology",

author = "Kapilan Radhakrishnan and Hadi Larijani and Tom Buggy",

note = "<p>Paper presented at the International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS10), Ottowa, Canada, 11-14 July 2010. Conference website: <a href={"}http://atc.udg.edu/SPECTS2010/{"}>http://atc.udg.edu/SPECTS2010/</a></p>",

year = "2010",

language = "English",

isbn = "9781565553408 ",

pages = "380--386 ",

booktitle = "2010 International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS)",

publisher = "IEEE",

}

TY - GEN

T1 - A non-intrusive method to assess voice quality over internet

AU - Radhakrishnan, Kapilan

AU - Larijani, Hadi

AU - Buggy, Tom

N1 - <p>Paper presented at the International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS10), Ottowa, Canada, 11-14 July 2010. Conference website: <a href="http://atc.udg.edu/SPECTS2010/">http://atc.udg.edu/SPECTS2010/</a></p>

PY - 2010

Y1 - 2010

N2 - Voice over IP (VoIP) is an emerging service and has gained popularity in recent years. The most challenging task for a service provider is to provide and monitor better voice quality. The nature of quality of service (QoS) in VoIP networks is very variable and hence it is important to be able to measure the QoS offered by the system in real time with a low computational cost. In this paper, we discuss our new model to monitor and predict voice quality non-intrusively using Random Neural Networks (RNN). Our model is based on using network delay, delay variation (jitter), packet loss and different voice codecs as input.

AB - Voice over IP (VoIP) is an emerging service and has gained popularity in recent years. The most challenging task for a service provider is to provide and monitor better voice quality. The nature of quality of service (QoS) in VoIP networks is very variable and hence it is important to be able to measure the QoS offered by the system in real time with a low computational cost. In this paper, we discuss our new model to monitor and predict voice quality non-intrusively using Random Neural Networks (RNN). Our model is based on using network delay, delay variation (jitter), packet loss and different voice codecs as input.

KW - telecommunications

KW - voice quality

KW - internet

KW - communication technology

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-78649296227&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781565553408

SP - 380

EP - 386

BT - 2010 International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS)

PB - IEEE

ER -