Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017)

Music Instrument Classification using Nontonal MFCC

Authors
Yi Wu, Qi Wang, Ruolun Liu
Corresponding Author
Yi Wu
Available Online April 2017.
DOI
10.2991/fmsmt-17.2017.88How to use a DOI?
Keywords
Timbre recognition, nontonal MFCC, instrument classification.
Abstract

Combined with the sounding mechanism and cepstrum, a new model is proposed to describe the timbre more precisely, together with the nontonal Mel-frequency cepstral coefficients (NMFCC) derived from the nontonal spectral content which relates closely to the resonator. A better performance is observed from the experiment results of five classifiers over the isolated instrument samples of 13 instruments of different instrument families. The NMFCC method outperforms the one using MFCC with an accuracy rate of 97.7% for individual instruments.

Copyright
© 2017, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017)
Series
Advances in Engineering Research
Publication Date
April 2017
ISBN
10.2991/fmsmt-17.2017.88
ISSN
2352-5401
DOI
10.2991/fmsmt-17.2017.88How to use a DOI?
Copyright
© 2017, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Yi Wu
AU  - Qi Wang
AU  - Ruolun Liu
PY  - 2017/04
DA  - 2017/04
TI  - Music Instrument Classification using Nontonal MFCC
BT  - Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017)
PB  - Atlantis Press
SP  - 417
EP  - 420
SN  - 2352-5401
UR  - https://doi.org/10.2991/fmsmt-17.2017.88
DO  - 10.2991/fmsmt-17.2017.88
ID  - Wu2017/04
ER  -