# Machine Unlearning for Speaker-Agnostic Detection of Gender-Based Violence Condition in Speech

arXiv: https://arxiv.org/abs/2411.18177 · HTML: https://mlsanity.com/paper/2411.18177/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 42 references that are in the map.
- First posted on arXiv 27 Nov 2024.

## Builds on (most cited first, 6 of 6)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Machine Unlearning: A Survey](https://mlsanity.com/paper/2306.03558/) (2023)
- [Speaker-invariant Affective Representation Learning via Adversarial Training](https://mlsanity.com/paper/1911.01533/) (2019)
- [Quantifying disparities in intimate partner violence: a machine learning method to correct for underreporting](https://mlsanity.com/paper/2110.04133/) (2021)
- [Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives](https://mlsanity.com/paper/1809.08927/) (2018)
- [WEMAC: Women and Emotion Multi-modal Affective Computing dataset](https://mlsanity.com/paper/2203.00456/) (2022)

## Abstract (arXiv)

Gender-based violence is a pervasive public health issue that severely impacts women's mental health, often leading to conditions such as in anxiety, depression, post-traumatic stress disorder, and substance abuse. Identifying the combination of these various mental health conditions could then point to someone who is a victim of gender-based violence. And while speech-based artificial intelligence tools show as a promising solution for mental health screening, their performance often deteriorates when encountering speech from previously unseen speakers, a sign that speaker traits may be confounding factors. This study introduces a speaker-agnostic approach to detecting the gender-based violence victim condition from speech, aiming to develop robust artificial intelligence models capable of generalizing across speakers. By employing domain-adversarial training, we reduce the influence of speaker identity on model predictions, we achieve a 26.95% relative reduction in speaker identification accuracy while improving gender-based violence victim condition classification accuracy by 6.37% (relative). These results suggest that our models effectively capture paralinguistic biomarkers linked to the gender-based violence victim condition, rather than speaker-specific traits. Additionally, the model's predictions show moderate correlation with pre-clinical post-traumatic stress disorder symptoms, supporting the relevance of speech as a non-invasive tool for mental health monitoring. This work lays the foundation for ethical, privacy-preserving artificial intelligence systems to support clinical screening of gender-based violence survivors.