Gct: Gated Contextual Transformer for Sequential Audio Tagging.
Yuanbo HouYun WangWenwu WangDick BotteldoorenPublished in: ICASSP (2023)
Keyphrases
- multimedia
- fuzzy logic
- contextual information
- signal processing
- metadata
- audio video
- fault diagnosis
- visual information
- context sensitive
- audio visual
- image tagging
- semantic context
- audio stream
- neural network
- audio signals
- social tagging
- visual data
- music information retrieval
- sequential data
- distribution network
- multi modal
- low level
- expert systems
- artificial intelligence