Owing to the enormous growth of VoIP applications, an effective means of identifying VoIP is now essential for managing a number of network traffic issues, such as reserving bandwidth for VoIP traffic, assigning high priority for VoIP flows, or blocking VoIP calls to certain destinations. Because the protocols, port numbers, and codecs used by VoIP services are shifting toward proprietary, encrypted, and dynamic methods, traditional VoIP identification approaches, including port- and payload-based schemes, are now less effective. Developing a traffic identification scheme that can work for general VoIP flows is therefore of paramount importance.

In this paper, we propose a VoIP flow identification scheme based on the unique interaction pattern of human conversations. Our scheme is particularly useful for two reasons: 1) flow detection relies on human conversations rather than packet timing; thus, it is resistant to network variability; and 2) detection is based on a short sequence of voice activities rather than the whole packet stream. Hence, the scheme can operate as a traffc management module to provide QoS guarantees or block VoIP calls in real time. The performance evaluation, which is based on extensive real-life traffc traces, shows that the proposed method achieves an identification accuracy of 95% in the first 4 seconds of the detection period and 97% in 11 seconds.

Related paper:
- Quantifying Skype User Satisfaction
- Peer-to-Peer Application Recognition Based on Signaling Activity
- Inferring Speech Activities from Encrypted Skype Traffic

Chen-Chi Wu, Kuan-Ta Chen, Yu-Chun Chang, and Chin-Laung Lei, "Detecting VoIP Traffic Based on Human Conversation Patterns," In Proceedings of Principles Systems and Applications of IP Telecommunications 2008 (IPTCOMM 2008), 2008.

Full Text (PDF Format, 343 KB)

Slides (PDF Format, 598 KB)