<div dir="ltr"><div style="font-size:12.8px"><span style="font-size:12.8px">[Apologies for cross-postings]</span><br></div><div style="font-size:12.8px"><span style="font-size:12.8px"><br></span></div><div style="font-size:12.8px">=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*<wbr>=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*<wbr>=*=*=*=*</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"> ASVspoof 2017 CHALLENGE:</div><div style="font-size:12.8px"> Audio replay detection for automatic speaker verification anti-spoofing</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"> <a href="http://www.spoofingchallenge.org/" target="_blank">http://www.<wbr>spoofingchallenge.org/</a></div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px">=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*<wbr>=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*<wbr>=*=*=*=*</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"> Are you good at machine learning for audio signals? Are you good at discriminating 'fake' signals from authentic ones? Are you looking for new audio processing challenges? Do you work in the domain of speaker recognition?</div><div style="font-size:12.8px"> ASVspoof 2017 challenge might be for you!</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px">CHALLENGE TASK:</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"> Given a short clip of speech audio, determine whether it contains</div><div style="font-size:12.8px"> a GENUINE human voice (live recording), or a REPLAY recording (fake).</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"> You will be provided a development set containing genuine/replay labeled audio examples, along with further metadata such as speech content and the devices used in the replay recordings. Your task is to develop a system that assigns a</div><div style="font-size:12.8px"> single 'liveness' or 'genuineness' score value to new audio samples and to execute that system on a set of test files for which the ground truth is not provided. We provide a Matlab-based reference baseline method to kick-off quickly towards developing your new ideas!</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"> For more details, refer to the evaluation plan on the website:</div><div style="font-size:12.8px"> <a href="http://www.spoofingchallenge.org/" target="_blank">http://www.<wbr>spoofingchallenge.org/</a></div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px">BACKGROUND:</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"> The goal of the challenge series is to enhance the security of automatic speaker verification (ASV) systems from being intentionally circumvented using fake recordings, also known as 'spoofing attacks' or 'representation attacks' in the context of biometrics. ASVspoof 2017 is the second edition of a challenge kicked off in 2015, and the new perspective in ASVspoof 2017 are the replay attacks, especially 'unseen' attacks - for instance, containing replay environments, devices, and speakers that might be very different from those in the development data.</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"> Despite 'ASV' being in the challenge title, you do NOT require knowledge of automatic speaker verification: the task is a 'standalone' replay audio detection task that can be addressed as a generic acoustic pattern classification problem. We welcome as many new ideas to the problem as possible!</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px">SCHEDULE:</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"> Development data published: December 23rd, 2016</div><div style="font-size:12.8px"> Evaluation data published: February 10, 2017</div><div style="font-size:12.8px"> Evaluation set scores due: February 24, 2017</div><div style="font-size:12.8px"> Results available: March 3, 2017</div><div style="font-size:12.8px"> Interspeech paper deadline: March 14, 2017</div><div style="font-size:12.8px"> Metadata/keys published: May 2017</div><div style="font-size:12.8px"> Interspeech special session: August 2017</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px">REGISTRATION:</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"> Send a free-worded e-mail to <a href="mailto:asvspoof2017@cs.uef.fi" target="_blank">asvspoof2017@cs.uef.fi</a></div><div style="font-size:12.8px"> to register and obtain the dev data.</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px">ORGANIZERS:</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"> Tomi Kinnunen, University of Eastern Finland, FINLAND</div><div style="font-size:12.8px"> Nicholas Evans, Eurecom, FRANCE</div><div style="font-size:12.8px"> Junichi Yamagishi, University of Edinburgh, UK</div><div style="font-size:12.8px"> Kong Aik Lee, Institute for Infocomm Research, SINGAPORE</div><div style="font-size:12.8px"> Md Sahidullah, University of Eastern Finland, FINLAND</div><div style="font-size:12.8px"> Massimiliano Todisco, Eurecom, FRANCE</div><div style="font-size:12.8px"> Hector Delgado, Eurecom, FRANCE</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px">CONTACT:</div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"> <a href="mailto:asvspoof2017@cs.uef.fi" target="_blank">asvspoof2017@cs.uef.fi</a></div><div><br></div>-- <br><div class="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><font face="comic sans ms, sans-serif" size="2" color="#000000">Dr. Md Sahidullah<br>Post-doctoral researcher<br>School of Computing</font><div><font face="comic sans ms, sans-serif" size="2" color="#000000">University of Eastern Finland<br>Joensuu, P.O. Box 111 Finland- 80101</font></div><div><font face="comic sans ms, sans-serif" size="2" color="#000000">tel. +358-466250731<br>website: <a href="http://cs.joensuu.fi/~sahid/" target="_blank">http://cs.joensuu.fi/~sahid/</a></font></div></div></div></div></div></div></div></div></div>
</div>