Unsupervised Generative Adversarial Alignment Representation for Sheet music, Audio and Lyrics.
Donghuo ZengYi YuKeizo OyamaPublished in: BigMM (2020)
Keyphrases
- audio signals
- music information retrieval
- audio features
- music retrieval
- audio recordings
- digital music
- music genre classification
- music collections
- digital audio
- unsupervised learning
- audio signal
- generative model
- audio visual
- audio content
- acoustic features
- data driven
- music score
- feature set
- genre classification
- low level
- multimedia
- semi supervised
- pairwise
- content based music retrieval
- music emotion classification
- image representation
- multi modal
- signal processing
- multi agent