Third International conference on advances in communication, network and computing

Research Article

Automatic Music Transcription of Indian Classical Music into MIDI Data

Download
473 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-35615-5_55,
        author={Kalyani Akant and Rajesh Pande and Shyamkant Limaye},
        title={Automatic Music Transcription of Indian Classical Music into MIDI Data},
        proceedings={Third International conference on advances in communication, network and computing},
        proceedings_a={CNC},
        year={2012},
        month={12},
        keywords={Musical Transcription MIDI Fourier of Fourier Transform Parabolic Interpolation Shruti monophonic/polyphonic Raga},
        doi={10.1007/978-3-642-35615-5_55}
    }
    
  • Kalyani Akant
    Rajesh Pande
    Shyamkant Limaye
    Year: 2012
    Automatic Music Transcription of Indian Classical Music into MIDI Data
    CNC
    Springer
    DOI: 10.1007/978-3-642-35615-5_55
Kalyani Akant1,*, Rajesh Pande2,*, Shyamkant Limaye3,*
  • 1: Manoharbhai Patel Institute of Engineering and Technology
  • 2: ShriRamdeobaba College of Engineering and Management
  • 3: Jhulelal Institute of Technology
*Contact email: kalyaniakant@gmail.com, panderaj@yahoo.com, shyam_limaye@hotmail.com

Abstract

Musical transcription of sampled audio data is the process of taking a sequence of digital data corresponding to the sound waveform and extracting from it the symbolic information i.e. MIDI scores. In this work, two different approaches for transcription of Indian Classical Music are discussed, one with prior knowledge of Raga and another without it. For this purpose, pitch detection is done using Fourier of Fourier Transform with Parabolic Interpolation to spectral peaks. This method for pitch detection is very accurate and suitable for shrutis in Indian Classical Music. For polyphonic music, we performed source separation by classifying frames as monophonic/polyphonic one. These separated monophonic frames are handled by a monophonic transcription system. Finally results are shown with conversion of Raga audio sample into MIDI format.