# An Investigation Into Explainable Audio Hate Speech Detection

arXiv: https://arxiv.org/abs/2408.06065 · HTML: https://mlsanity.com/paper/2408.06065/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 12 Aug 2024.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [Predicting the Type and Target of Offensive Posts in Social Media](https://mlsanity.com/paper/1902.09666/) (2019)
- [End-to-End Neural Speaker Diarization with Permutation-Free Objectives](https://mlsanity.com/paper/1909.05952/) (2019)
- [One-step and Two-step Classification for Abusive Language Detection on Twitter](https://mlsanity.com/paper/1706.01206/) (2017)
- [Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection](https://mlsanity.com/paper/1804.03124/) (2018)
- [Emotion Based Hate Speech Detection using Multimodal Learning](https://mlsanity.com/paper/2202.06218/) (2022)
- [Speaker Diarization with Region Proposal Network](https://mlsanity.com/paper/2002.06220/) (2020)

## Built on by (most cited first, 3 of 3)

- [MM-HSD: Multi-Modal Hate Speech Detection in Videos](https://mlsanity.com/paper/2508.20546/) (2025)
- [Gen-AI for User Safety: A Survey](https://mlsanity.com/paper/2411.06606/) (2024)
- [LLMs-Integrated Automatic Hate Speech Recognition Using Controllable Text Generation Models](https://mlsanity.com/paper/2601.04654/) (2026)

## Abstract (arXiv)

Research on hate speech has predominantly revolved around detection and interpretation from textual inputs, leaving verbal content largely unexplored. While there has been limited exploration into hate speech detection within verbal acoustic speech inputs, the aspect of interpretability has been overlooked. Therefore, we introduce a new task of explainable audio hate speech detection. Specifically, we aim to identify the precise time intervals, referred to as audio frame-level rationales, which serve as evidence for hate speech classification. Towards this end, we propose two different approaches: cascading and End-to-End (E2E). The cascading approach initially converts audio to transcripts, identifies hate speech within these transcripts, and subsequently locates the corresponding audio time frames. Conversely, the E2E approach processes audio utterances directly, which allows it to pinpoint hate speech within specific time frames. Additionally, due to the lack of explainable audio hate speech datasets that include audio frame-level rationales, we curated a synthetic audio dataset to train our models. We further validated these models on actual human speech utterances and found that the E2E approach outperforms the cascading method in terms of the audio frame Intersection over Union (IoU) metric. Furthermore, we observed that including frame-level rationales significantly enhances hate speech detection accuracy for the E2E approach. Disclaimer The reader may encounter content of an offensive or hateful nature. However, given the nature of the work, this cannot be avoided.