# ViToSA: Audio-Based Toxic Spans Detection on Vietnamese Speech Utterances

arXiv: https://arxiv.org/abs/2506.00636 · HTML: https://mlsanity.com/paper/2506.00636/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 24 references that are in the map.
- First posted on arXiv 31 May 2025.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [PhoBERT: Pre-trained language models for Vietnamese](https://mlsanity.com/paper/2003.00744/) (2020)
- [A Large-scale Dataset for Hate Speech Detection on Vietnamese Social Media Texts](https://mlsanity.com/paper/2103.11528/) (2021)
- [Constructive and Toxic Speech Detection for Open-domain Social Media Comments in Vietnamese](https://mlsanity.com/paper/2103.10069/) (2021)
- [MuTox: Universal MUltilingual Audio-based TOXicity Dataset and Zero-shot Detector](https://mlsanity.com/paper/2401.05060/) (2024)
- [An Exploratory Analysis of the Relation Between Offensive Language and Mental Health](https://mlsanity.com/paper/2105.14888/) (2021)
- [DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances](https://mlsanity.com/paper/2110.07592/) (2021)
- [ViHOS: Hate Speech Spans Detection for Vietnamese](https://mlsanity.com/paper/2301.10186/) (2023)
- [PhoWhisper: Automatic Speech Recognition for Vietnamese](https://mlsanity.com/paper/2406.02555/) (2024)
- [ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing](https://mlsanity.com/paper/2310.11166/) (2023)
- [VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding](https://mlsanity.com/paper/2403.15882/) (2024)
- [Lightweight Toxicity Detection in Spoken Language: A Transformer-based Approach for Edge Devices](https://mlsanity.com/paper/2304.11408/) (2023)
- [Enhancing Multilingual Voice Toxicity Detection with Speech-Text Alignment](https://mlsanity.com/paper/2406.10325/) (2024)
- [ViHateT5: Enhancing Hate Speech Detection in Vietnamese With A Unified Text-to-Text Transformer Model](https://mlsanity.com/paper/2405.14141/) (2024)
- [Linguistic Analysis of Toxic Behavior in an Online Video Game](https://mlsanity.com/paper/1410.5185/) (2014)
- [The Sounds of Cyber Threats](https://mlsanity.com/paper/1805.08272/) (2018)

## Abstract (arXiv)

Toxic speech on online platforms is a growing concern, impacting user experience and online safety. While text-based toxicity detection is well-studied, audio-based approaches remain underexplored, especially for low-resource languages like Vietnamese. This paper introduces ViToSA (Vietnamese Toxic Spans Audio), the first dataset for toxic spans detection in Vietnamese speech, comprising 11,000 audio samples (25 hours) with accurate human-annotated transcripts. We propose a pipeline that combines ASR and toxic spans detection for fine-grained identification of toxic content. Our experiments show that fine-tuning ASR models on ViToSA significantly reduces WER when transcribing toxic speech, while the text-based toxic spans detection (TSD) models outperform existing baselines. These findings establish a novel benchmark for Vietnamese audio-based toxic spans detection, paving the way for future research in speech content moderation.