Long-term Conversation Analysis: Exploring Utility and Privacy
This work addresses privacy concerns for individuals in everyday conversation analysis, but it is incremental as it builds on existing anonymization techniques.
The paper tackled the problem of balancing utility and privacy in long-term conversation analysis by proposing a privacy-preserving feature extraction method combining McAdams coefficient and spectral smoothing, showing it maintains utility in voice activity detection and speaker diarization while improving privacy in speech recognition and speaker verification.
The analysis of conversations recorded in everyday life requires privacy protection. In this contribution, we explore a privacy-preserving feature extraction method based on input feature dimension reduction, spectral smoothing and the low-cost speaker anonymization technique based on McAdams coefficient. We assess the utility of the feature extraction methods with a voice activity detection and a speaker diarization system, while privacy protection is determined with a speech recognition and a speaker verification model. We show that the combination of McAdams coefficient and spectral smoothing maintains the utility while improving privacy.