The paper presents the key-finding algorithm based on music signature concept. proposed is a set of 2-D vectors which can be treated as compressed form representation musical content in space. Each vector represents different pitch class. Its direction determined by position corresponding major key circle fifths. length each reflects multiplicity (i.e. number occurrences) class piece or its fra...

Thanks to the development of the Internet, people can easily access a vast amount of music. This brings attention to application systems such as a melody-based music search service or music recommendation service. Extracting melodies from music is a crucial process to provide such services. This paper introduces a novel algorithm that can extract melodies from piano music. Since piano can produ...

Our algorithm focuses on Audio Music Mood Classification task. We propose two mid-level features which can catch the chord tension and roughness of the sound, which have crucial roles in making mood in the music. From the experiment with 132 exemplar songs which MIREX offers, we find that those two features increase the performance of the Audio Music Mood classification system.

Music interest is diverse yet enticing to be a part of knowledge discovery. It influences how people feel, study, work, etc. A lot things are considered in producing brand new music with its correlation genre. We have already collected the dataset that we can utilize this research, which history every song listened by several users total 20.000 records from million dataset. This study implement...