# Few-Shot Contrastive Adaptation for Audio Abuse Detection in Low-Resource Indic Languages

arXiv: https://arxiv.org/abs/2604.09094 · HTML: https://mlsanity.com/paper/2604.09094/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 38 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media](https://mlsanity.com/paper/1910.12574/) (2019)
- [Handling Bias in Toxic Speech Detection: A Survey](https://mlsanity.com/paper/2202.00126/) (2022)
- [MuTox: Universal MUltilingual Audio-based TOXicity Dataset and Zero-shot Detector](https://mlsanity.com/paper/2401.05060/) (2024)
- [ADIMA: Abuse Detection In Multilingual Audio](https://mlsanity.com/paper/2202.07991/) (2022)
- [T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification](https://mlsanity.com/paper/2306.04996/) (2023)
- [Integrated Parameter-Efficient Tuning for General-Purpose Audio Models](https://mlsanity.com/paper/2211.02227/) (2022)
- [Enhancing Multilingual Voice Toxicity Detection with Speech-Text Alignment](https://mlsanity.com/paper/2406.10325/) (2024)
- [ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality](https://mlsanity.com/paper/2505.15773/) (2025)
- [SynHate: Detecting Hate Speech in Synthetic Deepfake Audio](https://mlsanity.com/paper/2506.06772/) (2025)
- [Abusive Speech Detection in Indic Languages Using Acoustic Features](https://mlsanity.com/paper/2407.20808/) (2024)
- [AAT: Adapting Audio Transformer for Various Acoustics Recognition Tasks](https://mlsanity.com/paper/2401.10544/) (2024)

## Abstract (arXiv)

Abusive and hateful speech is increasingly spoken rather than written, surfacing in voice notes, calls, and short-form videos. Most detection systems still transcribe speech to text before classifying it, but transcription is unreliable for languages lacking strong speech recognisers, and it discards the tone and emotion that often carry the abuse itself. This paper examines whether abusive speech can instead be detected directly from audio, using CLAP, a model that learns a shared representation of sound and language, evaluated across ten Indic languages in the ADIMA dataset. A lightweight classifier trained on CLAP's existing audio representations, without adapting the model itself, comes within one to three points of a fully supervised system, and far outperforms prompting with no labelled examples at all. Further adaptation with a handful of labelled examples per language yields little extra benefit, varying unpredictably across languages. CLAP-based audio representations thus already offer a strong, inexpensive foundation for detecting abusive speech across languages, lowering the labelled data needed in practice.