'Warriors of the Word' - Deciphering Lyrical Topics in Music and Their Connection to Audio Feature Dimensions Based on a Corpus of Over 100, 000 Metal Songs.
Isabella Czedik-EysenbergOliver J. WieczorekChristoph ReuterPublished in: CoRR (2019)
Keyphrases
- audio features
- music information retrieval
- feature set
- text data
- audio signal
- music retrieval
- audio files
- music recommendation
- music collections
- audio signals
- word frequencies
- latent topics
- visual features
- audio visual
- music score
- digital music
- low level
- writing style
- genre classification
- audio recordings
- acoustic features
- keywords
- music genre classification
- text corpus
- english words
- topic models
- information retrieval
- feature selection
- multimedia
- co occurrence
- newspaper articles
- training corpus
- spontaneous speech
- information retrieval systems
- stop words
- word sense disambiguation
- audio content
- digital audio
- music scores
- statistical machine translation
- word counts
- automatic music genre classification
- linguistic information
- sentence level
- natural language text
- lexical features
- text mining
- speech music discrimination
- feature vectors
- data embedding
- word pairs
- polyphonic music
- text documents
- text classification
- information extraction