Temporal Sub-sampling of Audio Feature Sequences for Automated Audio Captioning.
Khoa NguyenKonstantinos DrossosTuomas VirtanenPublished in: CoRR (2020)
Keyphrases
- multimedia
- audio visual
- cepstral features
- hidden markov models
- signal processing
- visual information
- audio stream
- audio files
- temporal patterns
- audio features
- spatio temporal
- audio signals
- semi automated
- visual data
- temporal constraints
- emotion recognition
- temporal sequences
- cross modal
- digital video
- music score
- feature vectors