Voice quality in VoIP networks based on random neural networks

Hadi Larijani; Kapilan Radhakrishnan

doi:10.1109/ICN.2010.23

Voice quality in VoIP networks based on random neural networks

Hadi Larijani, Kapilan Radhakrishnan

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

Abstract

The growth of Internet has led to the development of many new applications and technologies. Voice over Internet Protocol (VoIP) is one of the fastest growing applications. Calculating the quality of calls has been a complex task. The ITU E-Model gives a framework to measure quality of VoIP calls but the MOS element is a subjective measure. In this paper, we discuss a novel method using Random Neural Network (RNN) to accurately predict the perceived quality of voice and more importantly to perform this on real-time traffic to overcome the drawbacks of available methods. The novelty of this model is that RNN model provides a non-intrusive method to accurately predict and monitor perceived voice quality for both listening and conversational voice. This method has learning capabilities and this makes it possible for it to adapt to any network changes without human interference.

Original language	English
Title of host publication	Proceedings of the 9th International Conference on Networks (ICN) 2010
Publisher	IEEE
ISBN (Print)	9780769539799
DOIs	https://doi.org/10.1109/ICN.2010.23
Publication status	Published - 1 Jan 2010

Keywords

communications technology
voice quality
random neural networks
engineering

Documents and Links

10.1109/ICN.2010.23

Cite this

@inproceedings{88945c54fbe546fab52df678ad8a4a6e,

title = "Voice quality in VoIP networks based on random neural networks",

abstract = "The growth of Internet has led to the development of many new applications and technologies. Voice over Internet Protocol (VoIP) is one of the fastest growing applications. Calculating the quality of calls has been a complex task. The ITU E-Model gives a framework to measure quality of VoIP calls but the MOS element is a subjective measure. In this paper, we discuss a novel method using Random Neural Network (RNN) to accurately predict the perceived quality of voice and more importantly to perform this on real-time traffic to overcome the drawbacks of available methods. The novelty of this model is that RNN model provides a non-intrusive method to accurately predict and monitor perceived voice quality for both listening and conversational voice. This method has learning capabilities and this makes it possible for it to adapt to any network changes without human interference.",

keywords = "communications technology, voice quality, random neural networks, engineering",

author = "Hadi Larijani and Kapilan Radhakrishnan",

note = "<p>Paper presented at the 9th International Conference on Networks (ICN) 2010, Menuires, France, 11-16 April 2010. Conference website:<a href={"}http://www.iaria.org/conferences2010/ICN10.html{"}> http://www.iaria.org/conferences2010/ICN10.html</a></p>",

year = "2010",

month = jan,

day = "1",

doi = "10.1109/ICN.2010.23",

language = "English",

isbn = "9780769539799",

booktitle = "Proceedings of the 9th International Conference on Networks (ICN) 2010",

publisher = "IEEE",

}

TY - GEN

T1 - Voice quality in VoIP networks based on random neural networks

AU - Larijani, Hadi

AU - Radhakrishnan, Kapilan

N1 - <p>Paper presented at the 9th International Conference on Networks (ICN) 2010, Menuires, France, 11-16 April 2010. Conference website:<a href="http://www.iaria.org/conferences2010/ICN10.html"> http://www.iaria.org/conferences2010/ICN10.html</a></p>

PY - 2010/1/1

Y1 - 2010/1/1

N2 - The growth of Internet has led to the development of many new applications and technologies. Voice over Internet Protocol (VoIP) is one of the fastest growing applications. Calculating the quality of calls has been a complex task. The ITU E-Model gives a framework to measure quality of VoIP calls but the MOS element is a subjective measure. In this paper, we discuss a novel method using Random Neural Network (RNN) to accurately predict the perceived quality of voice and more importantly to perform this on real-time traffic to overcome the drawbacks of available methods. The novelty of this model is that RNN model provides a non-intrusive method to accurately predict and monitor perceived voice quality for both listening and conversational voice. This method has learning capabilities and this makes it possible for it to adapt to any network changes without human interference.

AB - The growth of Internet has led to the development of many new applications and technologies. Voice over Internet Protocol (VoIP) is one of the fastest growing applications. Calculating the quality of calls has been a complex task. The ITU E-Model gives a framework to measure quality of VoIP calls but the MOS element is a subjective measure. In this paper, we discuss a novel method using Random Neural Network (RNN) to accurately predict the perceived quality of voice and more importantly to perform this on real-time traffic to overcome the drawbacks of available methods. The novelty of this model is that RNN model provides a non-intrusive method to accurately predict and monitor perceived voice quality for both listening and conversational voice. This method has learning capabilities and this makes it possible for it to adapt to any network changes without human interference.

KW - communications technology

KW - voice quality

KW - random neural networks

KW - engineering

U2 - 10.1109/ICN.2010.23

DO - 10.1109/ICN.2010.23

M3 - Conference contribution

SN - 9780769539799

BT - Proceedings of the 9th International Conference on Networks (ICN) 2010

PB - IEEE

ER -

Voice quality in VoIP networks based on random neural networks

Abstract

Keywords

Documents and Links

Fingerprint

Cite this