Blind signal decompositions for automatic transcription of polyphonic music: NMF and K-SVD on the benchmark

Abstract : This paper investigates on the behavior of two blind signal decomposition algorithms, non negative matrix factorization (NMF) and non negative K-SVD (NKSVD), in a polyphonic music transcription task. State-of-the-art transcription systems are based on a frame-byframe, low-level approach; blind systems could be an alternative to them. Two raw but effective audio-to-MIDI systems are proposed and evaluated. Performances are similar, but in favor of NMF, which is more robust to initialization, choice of the order and computationnally less costly.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/hal-00945282
Contributor : Roland Badeau <>
Submitted on : Monday, March 24, 2014 - 4:08:42 PM
Last modification on : Thursday, October 17, 2019 - 12:36:06 PM
Long-term archiving on: Tuesday, June 24, 2014 - 10:46:57 AM

File

icassp-07-bis.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00945282, version 1

Collections

Citation

Nancy Bertin, Roland Badeau, Gaël Richard. Blind signal decompositions for automatic transcription of polyphonic music: NMF and K-SVD on the benchmark. Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2007, Honolulu, Hawaii, United States. pp.65--68. ⟨hal-00945282⟩

Share

Metrics

Record views

258

Files downloads

579