Title :
Sentiment extraction in music
Author :
Katayose, Haruhiro ; Imai, Masakazu ; Inokuchi, Seiji
Author_Institution :
Dept. of Control Eng., Osaka Univ., Japan
Abstract :
Sentiments are extracted from real performance through three steps: transcription, musical primitive analysis, and music understanding. In the transcription step, the acoustic signal is transformed into notes. Musical primitives such as chord progression, melody, rhythm, and tempo are analyzed from the notes using musical knowledge. Musical primitives are meaningful for the atmosphere of music. Sentiments are extracted by firing the heuristic rules representing the relation between musical primitives and sentiments for music understanding
Keywords :
computerised pattern recognition; music; psychology; chord progression; computerised pattern recognition; melody; music understanding; musical primitive analysis; psychology; rhythm; sentiment extraction; tempo; transcription; Artificial intelligence; Cognition; Control systems; Data mining; Humans; Multiple signal classification; Music; Performance analysis; Rhythm; Time frequency analysis;
Conference_Titel :
Pattern Recognition, 1988., 9th International Conference on
Conference_Location :
Rome
Print_ISBN :
0-8186-0878-1
DOI :
10.1109/ICPR.1988.28447
