Score-Informed Voice Separation For Piano Recordings (ISMIR 2011)

Abstract: The decomposition of a monaural audio recording into musically meaningful sound sources or voices constitutes a fundamental problem in music information retrieval. In this paper, we consider the task of separating a monaural piano recording into two sound sources (or voices) that correspond to the left hand and the right hand. Since in this scenario the two sources share many physical properties, sound separation approaches identifying sources based on their spectral envelope are hardly applicable. Instead, we propose a score-informed approach, where explicit note events specified by the score are used to parameterize the spectrogram of a given piano recording. This parameterization then allows for constructing two spectrograms considering only the notes of the left hand and the right hand, respectively. Finally, inversion of the two spectrograms yields the separation result. First experiments show that our approach, which involves high-resolution music synchronization and parametric modeling techniques, yields good results for realworld non-synthetic piano recordings.

For further details, see 2011_EwertMueller_VoiceSeparationPiano_ISMIR.pdf

@inproceedings{EwertMueller11_VoiceSeparation_ISMIR,
  author = {Sebastian Ewert and Meinard M{\"u}ller},
  title = {Score-Informed Voice Separation For Piano Recordings},
  booktitle = {Proceedings of the International Society for Music Information Retrieval Conference({ISMIR})},
  pages = {245--250},
  address = {Miami, USA},
  year = {2011}
}

Experimental Results

The interpretations of Beethoven's Op. 031 No. 2 and Op. 111 deviate in parts from the written score and are included for illustrative purposes.

Links

• Dipl.-Inform. Sebastian Ewert, Multimedia Signal Processing Group, Bonn University
• PD Dr. Meinard Müller, Multimedia Information Retrieval Group, Max-Planck Institut für Informatik
  

• Homepage
• Experimental results
• Links