Privacy versus Emotion Preservation Trade-offs in Emotion-Preserving Speaker Anonymization

Autor:	Cai, Zexin, Xinyuan, Henry Li, Garg, Ashi, García-Perera, Leibny Paola, Duh, Kevin, Khudanpur, Sanjeev, Andrews, Nicholas, Wiesner, Matthew
Rok vydání:	2024
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Advances in speech technology now allow unprecedented access to personally identifiable information through speech. To protect such information, the differential privacy field has explored ways to anonymize speech while preserving its utility, including linguistic and paralinguistic aspects. However, anonymizing speech while maintaining emotional state remains challenging. We explore this problem in the context of the VoicePrivacy 2024 challenge. Specifically, we developed various speaker anonymization pipelines and find that approaches either excel at anonymization or preserving emotion state, but not both simultaneously. Achieving both would require an in-domain emotion recognizer. Additionally, we found that it is feasible to train a semi-effective speaker verification system using only emotion representations, demonstrating the challenge of separating these two modalities. Comment: accepted by 2024 IEEE Spoken Language Technology Workshop
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2409.03655 Zobrazit plný text záznamu View this record from Arxiv