Reprogramming Self-supervised Learning-based Speech Representations For Speaker Anonymization

Abstract

Current speaker anonymization methods, especially with self-supervised learning (SSL) models, require massive computational resources when hiding speaker identity. This paper proposes an effective and parameter-efficient speaker anonymization method based on recent End-to-End model reprogramming technology. To improve the anonymization performance, we first extract speaker representation from large SSL models as the speaker identifies. To hide the speaker's identity, we reprogram the speaker representation by adapting the speaker to a pseudo domain. Extensive experiments are carried out on the VoicePrivacy Challenge (VPC) 2022 datasets to demonstrate the effectiveness of our proposed parameter-efficient learning anonymization methods. Additionally, while achieving comparable performance with the VPC 2022 strong baseline 1.b, our approach consumes less computational resources during anonymization.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keychen2023reprogramming

Related papers

• Language-independent Speaker Anonymization Approach Using Self-supervised Pre-trained Models (2022)9.92
• Analyzing Language-independent Speaker Anonymization Framework Under Unseen Conditions (2022)8.09
• Self-supervised Speech Representations Preserve Speech Characteristics While Anonymizing Voices (2022)0.00
• Speaker Anonymization Using Neural Audio Codec Language Models (2023)10.97
• SALT: Distinguishable Speaker Anonymization Through Latent Space Transformation (2023)9.88
• On-device Speaker Anonymization Of Acoustic Embeddings For ASR Based Onflexible Location Gradient Reversal Layer (2023)0.00
• Asynchronous Voice Anonymization Using Adversarial Perturbation On Speaker Embedding (2024)7.16
• NPU-NTU System For Voice Privacy 2024 Challenge (2024)7.16