Browse > Article
http://dx.doi.org/10.5916/jkosme.2012.36.8.1129

NMF Based Music Transcription Using Feature Vector Database  

Shin, Ok Keun (한국해양대학교 IT공학부)
Ryu, Da Hyun (한국해양대학교 IT공학부)
Abstract
To employ NMF to transcribe music by extracting feature matrix and weight matrix at the same time, it is necessary to know in advance the dimension of the feature matrix, and to determine the pitch of each extracted feature vector. Another drawback of this approach is that it becomes more difficult to accurately extract the feature matrix as the number of pitches included in the target music increases. In this study, we prepare a feature matrix database, and apply the matrix to transcribe real music. Transcription experiments are conducted by applying the feature matrix to the music played on the same piano on which the feature matrix is extracted, as well as on the music played on another piano. These results are also compared to those of another experiment where the feature matrix and weight matrix are extracted simultaneously, without making use of the database. We could observe that the proposed method outperform the method in which the two matrices are extracted at the same time.
Keywords
Music transcription; NMF; Feature matrix; Weight matrix; Database;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 P. Smaragdis, "Redundancy reduction for computational audition, a unifying approach", Thesis, Ph.D, MIT, 2001.
2 P. Smaragdis and C. B. Judith, "Non-negative matrix factorization for polyphonic music transcription", Proceeding IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, pp.177-180, 2003.
3 A. CICHOCKI and R. ZDUNEK, "Regularized alternating least squares algorithms for non-negative matrix/tensor factorization", Lecture Notes in Computer Science, Vol. 4493, Springer, pp. 793-802, 2007.
4 S. H. Park et al. "Music transcription using non-negative matrix factorization", The Journal of the Acoustical Society of Korea, vol. 29, no.2, pp.102-110, 2010. (in Korean).   과학기술학회마을
5 L. I. Ortiz-Berenguer et al. "Piano transcription using pattern recognition: aspects on parameter extraction", Proceeding of 7th international Conference on Digital Audio Effects, Naples, Italy, pp.212-216, Oct. 5-8, 2004.
6 Deutsche Grammophon, Wilhelm Kempff, (CD) Ludwig van Beethoven Klaviersonaten, No. 14 op27, (moonlight), West Germany, 1965.
7 K. D. Martin, Automatic Transcription of Simple Polyphonic Music: Robust Front End Processing, MIT Media Laboratory Perceptual Computing Section Technical Report, no. 399, pp. 1-11, 1996.
8 D. D. Lee and H. S. Seung, "Learning the parts of objects by non-negative matrix factorization", Nature, vol. 401, pp. 788-791, 1999.   DOI   ScienceOn
9 D. D Lee and H. S. Seung, "Algorithms for non-negative matrix factorization", Neural Information Processing Systems, pp. 556-562, 2000.