GCT: Gated Contextual Transformer for Sequential Audio Tagging.
Yuanbo HouYun WangWenwu WangDick BotteldoorenPublished in: CoRR (2022)
Keyphrases
- contextual information
- metadata
- fuzzy logic
- signal processing
- context sensitive
- multimedia
- high voltage
- audio visual
- semantic context
- audio signals
- multimedia information
- visual data
- knowledge base
- visual information
- audio recordings
- audio stream
- part of speech
- cross modal
- speaker identification
- fault diagnosis
- context aware
- audio video
- digital audio
- low level
- cepstral features