This repository contains PyTorch implementation of our paper called Privacy-PORCUPINE, which is intended to provide more privacy protection for speech signals (which are quantized in an information bottleneck) using our recently proposed Space-Filling Vector Quantization technique together with a codebook resampling technique. Full Changelog: https://github.com/Speech-Interaction-Technology-Aalto-U/Privay-PORCUPINE/compare/v1.0...v1.1. The title and description of this software/code correspond with the situation when the software metadata was imported to ACRIS. The most recent version of metadata is available in the original repository.

2024