Polyphonic Music Transcription Using Weighted CQT and Non-Negative Matrix Factorization

Park SH, Lee S, Sung KM. Polyphonic Music Transcription Using Weighted CQT and Non-Negative Matrix Factorization. In: AES Conference: 42nd International Conference: Semantic Audio. Audio Engineering Society; 2011. Paper P1-2. Available from: https://aes.org/publications/elibrary-page/?id=15955

@inproceedings{Park2011_15955,
  author = {Park, Sang Ha and Lee, Seokjin and Sung, Koeng-Mo},
  title = {{Polyphonic Music Transcription Using Weighted CQT and Non-Negative Matrix Factorization}},
  booktitle = {AES Conference: 42nd International Conference: Semantic Audio},
  note = {Paper P1-2},
  year = {2011},
  month = jul,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=15955}
}

TY  - CPAPER
TI  - Polyphonic Music Transcription Using Weighted CQT and Non-Negative Matrix Factorization
AU  - Park, Sang Ha
AU  - Lee, Seokjin
AU  - Sung, Koeng-Mo
T2  - AES Conference: 42nd International Conference: Semantic Audio
M1  - Paper P1-2
PY  - 2011
DA  - 2011/07/06
UR  - https://aes.org/publications/elibrary-page/?id=15955
PB  - Audio Engineering Society
LA  - en
AB  - Non-negative Matrix Factorization (NMF) is a useful method in music transcription. It achieves high speed computing and high performance. However, low frequency components are not fully detected and frequency confusion occurs occasionally in the conventional NMF based transcription algorithm. We propose a music transcription method using NMF with Weighted Constant-Q Transform (WCQT) to solve this problem. The filter bank of CQT is the same as that of the Western music scale interval, so the frequency components are well analyzed. And the weights on the CQT compensate the relatively small energy in low frequencies. We successfully transcribed polyphonic piano music with the proposed transcription algorithm, and the performance was better than that of the conventional method.
ER  -