According to "The Daily Stat" from the Hardvard Business Review, sentences spoken over Skype can be identified with up to 83% accuracy under certain conditions, says a team of researchers led by Benoit Dupasquier of Queen's University of Belfast in the UK. The voice-over-internet service encrypts conversations, but that encryption provides users a false sense of security, the researchers say. A Skype spokesperson says the methods used in the research don't constitute a meaningful form of attack, and the company plans no changes in its encryption.
Here is the Abstract to the report conducted by Benoît Dupasquier, Stefan Burschka, Kieran McLaughlin and Sakir Sezer
International Journal of Information Security, 2010, Volume 9, Number 5, Pages 313-325.
Voice over IP (VoIP) has experienced a tremendous growth over the last few years and is now widely used among the population and for business purposes. The security of such VoIP systems is often assumed, creating a false sense of privacy. This paper investigates in detail the leakage of information from Skype, a widely used and protected VoIP application. Experiments have shown that isolated phonemes can be classified and given sentences identified. By using the dynamic time warping (DTW) algorithm, frequently used in speech processing, an accuracy of 60% can be reached. The results can be further improved by choosing specific training data and reach an accuracy of 83% under specific conditions. The initial results being speaker dependent, an approach involving the Kalman filter is proposed to extract the kernel of all training signals.
A copy of the research paper can be found here.