WaveTransformer: An Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information.
An TranKonstantinos DrossosTuomas VirtanenPublished in: EUSIPCO (2021)
Keyphrases
- temporal information
- user interaction
- knowledge acquisition
- making decisions
- prior knowledge
- learning process
- spatio temporal
- reinforcement learning
- end users
- keywords
- multiresolution
- online learning
- information sources
- information sharing
- spatial and temporal
- temporal reasoning
- visual data
- temporal evolution
- feature extraction