We present a comprehensive evaluation of the infuence of 'harmonic' and rhythmic sections contained in an audio file on automatic music genre classi cation. The study is performed using the ISMIS database composed of music files, which are represented by vectors of acoustic parameters describing low-level music features. Non-negative Matrix Factorization serves for blind separation of instrument components. Rhythmic components are identi ed and separated from the rest of the audio signals. Using such separated streams, it is possible to obtain information on the infuence of rhythmic and harmonic components on music genre recognition. Further, the original audio feature vectors stemming from the non-separated signal are extended with such that base exclusively on drum and harmonic sections. The impact of these new parameters on music genre classification is investigated comparing the 'basic' k-Nearest Neighbor classfWi er and Support Vector Machines.
Autorzy
- Aldona Rosner link otwiera się w nowej karcie ,
- Felix Weninger,
- Bjorn Schuller,
- Marcin Michalak,
- prof. dr hab. inż. Bożena Kostek link otwiera się w nowej karcie
Informacje dodatkowe
- Kategoria
- Aktywność konferencyjna
- Typ
- publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
- Język
- angielski
- Rok wydania
- 2013
