ViToSA: Audio-Based Toxic Spans Detection on Vietnamese Speech Utterances
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908388022026240 |
|---|---|
| author | Do, Huy Ba Huynh, Vy Le-Phuong Nguyen, Luan Thanh |
| author_facet | Do, Huy Ba Huynh, Vy Le-Phuong Nguyen, Luan Thanh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00636 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ViToSA: Audio-Based Toxic Spans Detection on Vietnamese Speech Utterances Do, Huy Ba Huynh, Vy Le-Phuong Nguyen, Luan Thanh Computation and Language 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. |
| title | ViToSA: Audio-Based Toxic Spans Detection on Vietnamese Speech Utterances |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.00636 |