IteraTTA: An Interface for Exploring Both Text Prompts and Audio Priors in Generating Music With Text-to-Audio Models.
Hiromu YakuraMasataka GotoPublished in: ISMIR (2023)
Keyphrases
- text graphics
- audio content
- information retrieval
- audio signals
- music scores
- multimedia
- keywords
- database
- music score
- audio visual
- cross media retrieval
- text retrieval
- text documents
- text mining
- free text
- music information retrieval
- text to speech
- digital audio
- user interface
- prior knowledge
- hidden markov models
- probabilistic model
- music genre classification
- audio files
- human language
- audio features
- text input
- signal processing
- music retrieval
- audio signal
- multi modal