Evaluating X-vector-based Speaker Anonymization under White-box Assessment
In the scenario of the Voice Privacy challenge, anonymization is achieved by converting all utterances from a source speaker to match the same target identity; this identity being randomly selected. In this context, an attacker with maximum knowledge about the anonymization system can not infer the target identity. This article proposed to constrain the target selection to a specific identity, i.e., removing the random selection of identity, to evaluate the extreme threat under a whitebox assessment (the attacker has complete knowledge about the system). Targeting a unique identity also allows us to investigate whether some target's identities are better than others to anonymize a given speaker.
Code (0)
등록된 구현이 없습니다.
Tasks
Speaker anonymizationSimilar Papers 제목 키워드 기반
Exploring the Importance of F0 Trajectories for Speaker Anonymization using X-vectors and Neural Waveform Models
Voice conversion for speaker anonymization is an emerging field in speech processing research. Many state-of-the-art approaches are based on the resynthesis of the phoneme posteriorgrams (PPG), the fundamental frequency …
ResynthesisSpeaker anonymizationVoice ConversionVocoder drift in x-vector-based speaker anonymization
State-of-the-art approaches to speaker anonymization typically employ some form of perturbation function to conceal speaker information contained within an x-vector embedding, then resynthesize utterances in the voice of…
Speaker anonymizationDesign Choices for X-vector Based Speaker Anonymization
The recently proposed x-vector based anonymization scheme converts any input voice into that of a random pseudo-speaker. In this paper, we present a flexible pseudo-speaker selection technique as a baseline for the first…
Speaker anonymizationSpeaker VerificationSpeaker Anonymization with Distribution-Preserving X-Vector Generation for the VoicePrivacy Challenge 2020
In this paper, we present a Distribution-Preserving Voice Anonymization technique, as our submission to the VoicePrivacy Challenge 2020. We observe that the challenge baseline system generates fake X-vectors which are ve…
Speaker anonymizationEvaluating Voice Conversion-based Privacy Protection against Informed Attackers
Speech data conveys sensitive speaker attributes like identity or accent. With a small amount of found data, such attributes can be inferred and exploited for malicious purposes: voice cloning, spoofing, etc. Anonymizati…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Speaker Verificationspeech-recognition+3