"Hardness" as a semantic audio descriptor for music using automatic feature extraction.
Isabella Czedik-EysenbergDenis KnaufChristoph ReuterPublished in: GI-Jahrestagung (2017)
Keyphrases
- feature extraction
- speech music discrimination
- audio signals
- audio features
- music information retrieval
- music score
- cepstral features
- feature representation
- music scores
- image processing
- local binary pattern
- preprocessing
- music genre classification
- audio recordings
- feature vectors
- gaussian mixture model
- automatic music genre classification
- dimensionality reduction
- automatic indexing
- feature set
- music retrieval
- face recognition
- audio signal
- speaker identification
- frequency domain
- semi automatic
- texture features
- semantic annotation
- music collections
- natural language
- polyphonic music
- extracted features
- object recognition
- visual information
- texture analysis
- semantic information
- gabor filters
- semantic similarity
- feature extractor
- principal component analysis
- digital audio
- np complete
- image classification
- audio content
- speech corpus
- texture descriptors
- multimedia
- feature selection
- wavelet transform