The VoicePrivacy 2020 Challenge: Results and findings
arXiv:2109.00648 · doi:10.1016/j.csl.2022.101362
Abstract
This paper presents the results and analyses stemming from the first VoicePrivacy 2020 Challenge which focuses on developing anonymization solutions for speech technology. We provide a systematic overview of the challenge design with an analysis of submitted systems and evaluation results. In particular, we describe the voice anonymization task and datasets used for system development and evaluation. Also, we present different attack models and the associated objective and subjective evaluation metrics. We introduce two anonymization baselines and provide a summary description of the anonymization systems developed by the challenge participants. We report objective and subjective evaluation results for baseline and submitted systems. In addition, we present experimental results for alternative privacy metrics and attack models developed as a part of the post-evaluation analysis. Finally, we summarize our insights and observations that will influence the design of the next VoicePrivacy challenge edition and some directions for future voice anonymization research.
Submitted to the Special Issue on Voice Privacy (Computer Speech and Language Journal - Elsevier); under review
References in corpus (8)
- Evaluating Voice Conversion-based Privacy Protection against Informed Attackers
- Privacy-preserving Voice Analysis via Disentangled Representations
- VoiceMask: Anonymize and Sanitize Voice Input on Mobile Devices
- Privacy attacks for automatic speech recognition acoustic models in a federated learning framework
- Voice-Indistinguishability: Protecting Voiceprint in Privacy-Preserving Speech Data Release
- Speaker De-identification System using Autoencoders and Adversarial Training
- Exploring the Importance of F0 Trajectories for Speaker Anonymization using X-vectors and Neural Waveform Models
- Speech Pseudonymisation Assessment Using Voice Similarity Matrices