An Adaptive Approach to Identify Genre in Music Videos Using Word2Vec Model

Abstract

Abstract-The vector representations of words presented by Word2Vec model have been shown to be very useful in many application developments due to the semantic information they convey. This paper proposes a similar form, the MusicGenre2Vec. MusicGenre2Vec represents the numerical genre features of music segments inside the vector with the intention to describe the phonetic systems of the tune segments in an excellent way. We are hoping the vector representations obtained in this way can describe more precisely the phonetic structures of the Music indicators, so the Music segments that sound alike would have vector representations close by within the space. This form of depiction is called MusicGenre2Vec in this paper. The proposed system gives 80% of accuracy in finding the Genre of a video song.