ViToSA is the first Vietnamese audio benchmark for toxic span detection, pairing fine-tuned ASR with text-based span models to locate toxic phrases in speech.
The process is outlined in the following sections: data pre-processing, evaluation metrics, and speech recognition experimental results
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ViToSA: Audio-Based Toxic Spans Detection on Vietnamese Speech Utterances
ViToSA is the first Vietnamese audio benchmark for toxic span detection, pairing fine-tuned ASR with text-based span models to locate toxic phrases in speech.