Towards Robust Unsupervised Disentanglement of Sequential Data - A Case Study Using Music Audio.
Yin-Jyun LuoSebastian EwertSimon DixonPublished in: CoRR (2022)
Keyphrases
- sequential data
- hidden markov models
- audio signals
- music information retrieval
- sequential patterns
- fixed length
- sequential pattern mining
- pattern mining
- audio signal
- sequence data
- music score
- automatic music genre classification
- data mining
- audio recordings
- audio files
- audio features
- variable length
- pattern discovery
- information extraction
- spatio temporal
- multiscale
- music retrieval
- multiresolution
- musical instruments
- change point detection
- audio content
- feature extraction