The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation.
Ilaria MancoBenno WeckSeungheon DohMinz WonYixiao ZhangDmitry BogdanovYusong WuKe ChenPhilip TovstoganEmmanouil BenetosElio QuintonGyörgy FazekasJuhan NamPublished in: CoRR (2023)
Keyphrases
- audio features
- audio files
- audio signals
- polyphonic music
- feature set
- music information retrieval
- visual features
- music score
- music retrieval
- audio content
- audio signal
- audio visual
- programming language
- temporal information
- acoustic features
- multimedia
- information retrieval systems
- text to speech
- human language
- music scores
- spanish language
- automatic music genre classification
- million images
- manually annotated
- text data
- text mining
- natural language