| Dear colleagues, Interspeech 2013 includes a special submission track on vulnerabilities of speaker recognition systems. Hope that many of you will consider submitting papers. Studies on synthesis / voice conversion / playback attacks, impersonation and detection of such attacks are possible topics (but not limited to them). The submission deadline is the same as for regular papers (March 18). Feel free to distribute this announcement to your colleagues! Spoofing and countermeasures for automatic speaker verification It is widely acknowledged that most biometric systems are vulnerable to imposture or spoofing attacks. While vulnerabilities and countermeasures for other biometric modalities have been widely studied, automatic speaker recognition systems remain vulnerable. This special session aims to promote the study of spoofing and countermeasures for the speech modality. We invite submissions with an emphasis on new countermeasures in addition to papers with a focus on previously unconsidered vulnerabilities, new databases, evaluation protocols and metrics for the assessment of automatic speaker recognition in the face of spoofed samples. In particular, we aim to stimulate new interest from colleagues working in related fields, e.g. voice conversion and speech synthesis, whose participation is sought for the design of future evaluations. Feel free to contact us for more details: Nicholas Evans, EURECOM, evans@xxxxxxxxxx Tomi Kinnunen, University of Eastern Finland, tkinnu@xxxxxxxxx Sebastien Marcel, IDIAP Research Institute, marcel@xxxxxxxx Junichi Yamagishi, University of Edinburgh, jyamagis@xxxxxxxxxxxx |
The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336.