IteraTTA: An interface for exploring both text prompts and audio priors in generating music with text-to-audio models.
Hiromu YakuraMasataka GotoPublished in: CoRR (2023)
Keyphrases
- text graphics
- audio content
- audio signals
- music information retrieval
- multimedia
- database
- music score
- keywords
- text documents
- text to speech
- audio features
- cross media retrieval
- spoken documents
- text mining
- visual information
- human language
- information retrieval
- free text
- text retrieval
- audio visual
- audio signal
- bayesian framework
- web documents
- text classification
- probabilistic model
- audio stream
- hidden markov models
- prior knowledge
- content based music retrieval