An automatic audio annotation pipeline using BEATs and CLAP filtering produces a 2130-hour dataset that yields 3.97% average accuracy gains on three domestic audio classification tasks.
It efficiently converts audio collected from various streaming platforms into high- quality training data with event annotations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TriA Pipeline: A Large-Scale Automatic Audio Annotation Pipeline For Audio Classification In Specific Scenarios
An automatic audio annotation pipeline using BEATs and CLAP filtering produces a 2130-hour dataset that yields 3.97% average accuracy gains on three domestic audio classification tasks.