Language independent on-off voice over IP source model with lognormal transitions

The recent explosive growth of voice over IP (VoIP) solutions calls for accurate modelling of VoIP traffic. This study presents measurements of ON and OFF periods of VoIP activity from a significantly large database of VoIP call recordings consisting of native speakers speaking in some of the world's most widely spoken languages. The impact of the languages and the varying dynamics of caller interaction on the ON and OFF period statistics are assessed. It is observed that speaker interactions dominate over language dependence which makes monologue-based data unreliable for traffic modelling. The authors derive a semi-Markov model which accurately reproduces the statistics of composite dialogue measurements.

[1]  Trang Dinh Dang,et al.  Fractal analysis and modeling of VoIP traffic , 2004, 11th International Telecommunications Network Strategy and Planning Symposium. NETWORKS 2004,.

[2]  Hyeong-Ho Lee,et al.  A Study of On-Off Characteristics of Conversational Speech , 1986, IEEE Trans. Commun..

[3]  P.V. Mockapetris Telephony's next act , 2006, IEEE Spectrum.

[4]  Kazi M. Ahmed,et al.  Analysis and Modeling of Voice over IP Traffic in the Real Network , 2006, IEICE Trans. Inf. Syst..

[5]  Brigitte Zellner,et al.  Pauses and the temporal structure of speech , 1995 .

[6]  Ward Whitt,et al.  Characterizing Superposition Arrival Processes in Packet Multiplexers for Voice and Data , 1986, IEEE J. Sel. Areas Commun..

[7]  Estelle Campione,et al.  A large-scale multilingual study of silent pause duration , 2002, Speech Prosody 2002.

[8]  M. Menth,et al.  Source Models for Speech Traffic Revisited , 2009, IEEE/ACM Transactions on Networking.

[9]  Charles Elkan,et al.  Expectation Maximization Algorithm , 2010, Encyclopedia of Machine Learning.

[10]  Brian MacWhinney,et al.  The Talkbank Project , 2007 .

[11]  Randy H. Katz,et al.  Characterizing packet audio streams from Internet multimedia applications , 2002, 2002 IEEE International Conference on Communications. Conference Proceedings. ICC 2002 (Cat. No.02CH37333).

[12]  J. Gruber,et al.  A Comparison of Measured and Calculated Speech Temporal Parameters Relevant to Speech Activity Detection , 1982, IEEE Trans. Commun..

[13]  Samy A. Mahmoud,et al.  A model for generating on-off patterns in conversational speech, including short silence gaps and the effects of interaction between parties , 1994 .

[14]  B. Goode,et al.  Voice over Internet protocol (VoIP) , 2002, Proc. IEEE.

[15]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[16]  Paul T. Brady,et al.  A model for generating on-off speech patterns in two-way conversation , 1969 .