To search, Click below search items.


All Published Papers Search Service


Identification of Spam over Internet Telephony through Acoustic Fingerprint Technique


Nitikesh S. Thakare, Avinash P.Wadhe


Vol. 14  No. 5  pp. 87-90


Spam has posed a serious problem for users of email since its infancy. Today, automated strategies are required to deal with the massive amount of spam traffic. In an email setting, we have a significant chance to quarantine incoming emails to check if they are spam or a virus. In fact, as Simple Mail Transfer Protocol (SMTP) allows a repeated negotiation step between the sender and receiver, there are plenty of chances to tap into the negotiation steps and quarantine emails. Research in this area includes various approaches ? such as Bayesian-based, content-based, DNS based or signature-based and sometimes combines methods for a hybrid approach. As opposed to email protocols represented by SMTP, VoIP does not tolerate any negotiation in the signaling step or screening of content because of its slim delay limitation. Thus, it is harder to implement any Spam over Internet Telephony (SPIT) protection or control algorithms in a VoIP setting. SPIT detection and mitigation can also be based on the caller's audio data and that’s why in order to identify such technique is required. Thus we approaches, uses of the audio identification techniques (similar to music identification) to detect calls with identical audio data including certain degradations (e.g., noise and different audio codecs) called as robust Acoustic fingerprint is derived from spectral parameters of the audio data and replayed calls are identified by a comparison of fingerprints for dealing with spam and its voice means precisely