CORTEXA
← Browse

Anderson Augusma

1 paper indexed

arxiveess.SPcs.AI2026-07-07

Listen to the Features: Voice Anonymization Driven by Content Embedding Matching over Signal Reconstruction

Adrien Schneider, Kacper Zabkowski, Anderson Augusma, Frédérique Letué, Maria Camila Pinzon, Dominique Vaufreydaz

The paper presents a voice anonymization model focusing on preserving content rather than producing realistic speech. It relies on content embeddings extracted from a frozen pretrained wav2vec2 encoder. These embeddings are decoded into an anonymized signal using vector quantizat…

View free PDFSource page