In this work, we pioneer the study of Machine Unlearning (MU) for Paralinguistic Speech Processing (PSP). We focus on two key PSP tasks: Speech Emotion Recognition (SER) and Depression Detection (DD). To this end, we propose, SISA++, a novel extension to previous state-of-the-art (SOTA) MU method, SISA by merging models trained on different shards with weight-averaging. With such modifications, we show that SISA++ preserves performance more in comparison to SISA after unlearning in benchmark SER (CREMA-D) and DD (E-DAIC) datasets. Also, to guide future research for easier adoption of MU for PSP, we present ``cookbook recipes'' - actionable recommendations for selecting optimal feature representations and downstream architectures that can mitigate performance degradation after the unlearning process.
Cite
@article{arxiv.2506.02230,
title = {Towards Machine Unlearning for Paralinguistic Speech Processing},
author = {Orchid Chetia Phukan and Girish and Mohd Mujtaba Akhtar and Shubham Singh and Swarup Ranjan Behera and Vandana Rajan and Muskaan Singh and Arun Balaji Buduru and Rajesh Sharma},
journal= {arXiv preprint arXiv:2506.02230},
year = {2025}
}