Distinctive And Natural Speaker Anonymization Via Singular Value Transformation-assisted Matrix

Abstract

Speaker anonymization is an effective privacy protection solution that aims to conceal the speaker's identity while preserving the naturalness and distinctiveness of the original speech. Mainstream approaches use an utterance-level vector from a pre-trained automatic speaker verification (ASV) model to represent speaker identity, which is then averaged or modified for anonymization. However, these systems suffer from deterioration in the naturalness of anonymized speech, degradation in speaker distinctiveness, and severe privacy leakage against powerful attackers. To address these issues and especially generate more natural and distinctive anonymized speech, we propose a novel speaker anonymization approach that models a matrix related to speaker identity and transforms it into an anonymized singular value transformation-assisted matrix to conceal the original speaker identity. Our approach extracts frame-level speaker vectors from a pre-trained ASV model and employs an attention mecha

Stats

• citations14
• S2 citations—
• github stars0
• HF likes0
• heat score8.82
• arxiv keyyao2024distinctive

Related papers

• Speaker Anonymization Using X-vector And Neural Waveform Models (2019)0.00
• SALT: Distinguishable Speaker Anonymization Through Latent Space Transformation (2023)9.88
• MUSA: Multi-lingual Speaker Anonymization Via Serial Disentanglement (2024)0.00
• Language-independent Speaker Anonymization Approach Using Self-supervised Pre-trained Models (2022)9.92
• Asynchronous Voice Anonymization Using Adversarial Perturbation On Speaker Embedding (2024)7.16
• Speaker Anonymization Using Neural Audio Codec Language Models (2023)10.97
• Reprogramming Self-supervised Learning-based Speech Representations For Speaker Anonymization (2023)2.26
• Speaker Anonymization With Distribution-preserving X-vector Generation For The Voiceprivacy Challenge 2020 (2020)0.00