Non-negative matrix factorization (NMF) is widely used for music transcription because of its efficiency. However, the conventional NMF-based music transcription algorithm often causes harmonic confusion errors or time split-up errors, because the NMF decomposes the time-frequency data according to the activated frequency in its time. To solve these problems, we proposed an NMF with temporal continuity and harmonicity constraints. The temporal continuity constraint prevented the time split-up of the continuous time components, and the harmonicity constraint helped to bind the fundamental with harmonic frequencies by reducing the additional octave errors. The transcription performance of the proposed algorithm was compared with that of the conventional algorithms, which showed that the proposed method helped to reduce additional false errors and increased the overall transcription performance.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Sang Ha PARK, Seokjin LEE, Koeng-Mo SUNG, "Polyphonic Music Transcription by Nonnegative Matrix Factorization with Harmonicity and Temporality Criteria" in IEICE TRANSACTIONS on Fundamentals,
vol. E95-A, no. 9, pp. 1610-1614, September 2012, doi: 10.1587/transfun.E95.A.1610.
Abstract: Non-negative matrix factorization (NMF) is widely used for music transcription because of its efficiency. However, the conventional NMF-based music transcription algorithm often causes harmonic confusion errors or time split-up errors, because the NMF decomposes the time-frequency data according to the activated frequency in its time. To solve these problems, we proposed an NMF with temporal continuity and harmonicity constraints. The temporal continuity constraint prevented the time split-up of the continuous time components, and the harmonicity constraint helped to bind the fundamental with harmonic frequencies by reducing the additional octave errors. The transcription performance of the proposed algorithm was compared with that of the conventional algorithms, which showed that the proposed method helped to reduce additional false errors and increased the overall transcription performance.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E95.A.1610/_p
Copy
@ARTICLE{e95-a_9_1610,
author={Sang Ha PARK, Seokjin LEE, Koeng-Mo SUNG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Polyphonic Music Transcription by Nonnegative Matrix Factorization with Harmonicity and Temporality Criteria},
year={2012},
volume={E95-A},
number={9},
pages={1610-1614},
abstract={Non-negative matrix factorization (NMF) is widely used for music transcription because of its efficiency. However, the conventional NMF-based music transcription algorithm often causes harmonic confusion errors or time split-up errors, because the NMF decomposes the time-frequency data according to the activated frequency in its time. To solve these problems, we proposed an NMF with temporal continuity and harmonicity constraints. The temporal continuity constraint prevented the time split-up of the continuous time components, and the harmonicity constraint helped to bind the fundamental with harmonic frequencies by reducing the additional octave errors. The transcription performance of the proposed algorithm was compared with that of the conventional algorithms, which showed that the proposed method helped to reduce additional false errors and increased the overall transcription performance.},
keywords={},
doi={10.1587/transfun.E95.A.1610},
ISSN={1745-1337},
month={September},}
Copy
TY - JOUR
TI - Polyphonic Music Transcription by Nonnegative Matrix Factorization with Harmonicity and Temporality Criteria
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1610
EP - 1614
AU - Sang Ha PARK
AU - Seokjin LEE
AU - Koeng-Mo SUNG
PY - 2012
DO - 10.1587/transfun.E95.A.1610
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E95-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2012
AB - Non-negative matrix factorization (NMF) is widely used for music transcription because of its efficiency. However, the conventional NMF-based music transcription algorithm often causes harmonic confusion errors or time split-up errors, because the NMF decomposes the time-frequency data according to the activated frequency in its time. To solve these problems, we proposed an NMF with temporal continuity and harmonicity constraints. The temporal continuity constraint prevented the time split-up of the continuous time components, and the harmonicity constraint helped to bind the fundamental with harmonic frequencies by reducing the additional octave errors. The transcription performance of the proposed algorithm was compared with that of the conventional algorithms, which showed that the proposed method helped to reduce additional false errors and increased the overall transcription performance.
ER -