2000 character limit reached
Introducing the VoicePrivacy Initiative (2005.01387v3)
Published 4 May 2020 in cs.CL
Abstract: The VoicePrivacy initiative aims to promote the development of privacy preservation tools for speech technology by gathering a new community to define the tasks of interest and the evaluation methodology, and benchmarking solutions through a series of challenges. In this paper, we formulate the voice anonymization task selected for the VoicePrivacy 2020 Challenge and describe the datasets used for system development and evaluation. We also present the attack models and the associated objective and subjective evaluation metrics. We introduce two anonymization baselines and report objective evaluation results.
- Natalia Tomashenko (32 papers)
- Brij Mohan Lal Srivastava (13 papers)
- Xin Wang (1306 papers)
- Emmanuel Vincent (44 papers)
- Andreas Nautsch (26 papers)
- Junichi Yamagishi (178 papers)
- Nicholas Evans (73 papers)
- Jose Patino (27 papers)
- Massimiliano Todisco (55 papers)
- Jean-François Bonastre (14 papers)
- Paul-Gauthier Noé (10 papers)