Voice quality in VoIP networks based on random neural networks

Hadi Larijani, Kapilan Radhakrishnan

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    13 Citations (Scopus)

    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 languageEnglish
    Title of host publicationProceedings of the 9th International Conference on Networks (ICN) 2010
    PublisherIEEE
    ISBN (Print)9780769539799
    DOIs
    Publication statusPublished - 1 Jan 2010
    EventNinth International Conference on Networks - Hôtel Latitudes Les Bruyeres, Les Menuires, France
    Duration: 11 Apr 201016 Apr 2010
    https://www.iaria.org/conferences2010/ICN10.html (Link to conference website)

    Conference

    ConferenceNinth International Conference on Networks
    Abbreviated titleICN 2010
    Country/TerritoryFrance
    CityLes Menuires
    Period11/04/1016/04/10
    Internet address

    Keywords

    • communications technology
    • voice quality
    • random neural networks
    • engineering

    Fingerprint

    Dive into the research topics of 'Voice quality in VoIP networks based on random neural networks'. Together they form a unique fingerprint.

    Cite this