Chord Recognition in Music Using a Robust Pitch Class Profile (PCP) Feature and Support Vector Machines (SVM)

Suwatchai Kamonsantiroj, Lita Wannatrong, Luepol Pipanmaekaporn

Abstract


Music is the most direct and effective means to express emotion, and the effective identification of music works can help us better understand the works and realize the correct interpretation of music. This paper takes robust PCP feature and SVM as the research object. Firstly, the related concepts of terms and a large number of robust CFO description chord spectrum methods used in audio analysis are introduced. Secondly, it expounds the correlation between SVM and speech tonality, designs the system of music chord recognition, tests the performance of the system, and focuses on the test in the direction of recognition rate. Finally, the test results show that the system greatly improves the recognition of music chords with the support of robustness feature optimization and SVM pattern.


Article Metrics

Abstract: 867 Viewers PDF: 559 Viewers

Keywords


Robustness; PCP Feature; SVM; Music Chord

Full Text:

PDF


Refbacks

  • There are currently no refbacks.



Barcode

IJIIS: International Journal of Informatics and Information Systems

ISSN:2579-7069 (Online)
Organized by:Departement of Information System, Universitas Amikom Purwokerto, IndonesiaFaculty of Computing and Information Science, Ain Shams University, Cairo, Egypt
Website:www.ijiis.org
Email:husniteja@uinjkt.ac.id (publication issues)
  taqwa@amikompurwokerto.ac.id (managing editor)
  contact@ijiis.org (technical & paper handling issues)

 This work is licensed under a Creative Commons Attribution-ShareAlike 4.0