Generating lyrics with variational autoencoder and multi-modal artist embeddings.
Olga VechtomovaHareesh BahuleyanAmirpasha GhabussiVineet JohnPublished in: CoRR (2018)
Keyphrases
- multi modal
- music information retrieval
- multi modality
- audio visual
- high dimensional
- cross modal
- optical flow
- low dimensional
- music retrieval
- audio features
- video search
- music emotion classification
- dimensionality reduction
- high dimensional data
- single modality
- image annotation
- semantic concepts
- image processing
- medical imaging
- semantic information
- image segmentation