Target speaker anonymization in multi-speaker recordings
This work addresses privacy needs in call centers by enabling targeted anonymization, but it is incremental as it builds on existing single-speaker methods.
The study tackled the problem of anonymizing only a target speaker in multi-speaker conversational audio, such as in call centers, by exploring strategies and proposing improved evaluation methods to address gaps in privacy and utility assessment.
Most of the existing speaker anonymization research has focused on single-speaker audio, leading to the development of techniques and evaluation metrics optimized for such condition. This study addresses the significant challenge of speaker anonymization within multi-speaker conversational audio, specifically when only a single target speaker needs to be anonymized. This scenario is highly relevant in contexts like call centers, where customer privacy necessitates anonymizing only the customer's voice in interactions with operators. Conventional anonymization methods are often not suitable for this task. Moreover, current evaluation methodology does not allow us to accurately assess privacy protection and utility in this complex multi-speaker scenario. This work aims to bridge these gaps by exploring effective strategies for targeted speaker anonymization in conversational audio, highlighting potential problems in their development and proposing corresponding improved evaluation methodologies.