Joint Audio and Symbolic Conditioning for Temporally Controlled Text-to-Music Generation.
Or TalAlon ZivItai GatFelix KreukYossi AdiPublished in: CoRR (2024)
Keyphrases
- audio content
- music information retrieval
- audio signals
- text graphics
- text generation
- music score
- music scores
- audio features
- audio signal
- audio recordings
- music collections
- information retrieval
- multimedia
- digital audio
- music genre classification
- text data
- automatic music genre classification
- digital music
- music retrieval
- speech music discrimination
- multimedia content
- polyphonic music
- free text
- content based music retrieval
- cross media retrieval
- text documents
- database
- human language
- audio files
- text mining
- spatio temporal
- information retrieval systems
- text to speech
- semantic information
- natural language generation
- symbolic representation
- text retrieval
- musical instruments
- visual information
- genre classification
- multi modal
- keywords
- web documents
- metadata
- cross modal