Automatic Recognition of Isolated Monophonic Musical Instrument Sounds using kNNC

Kaminskyj, Ian; Czaszejko, Tadeusz

doi:10.1007/s10844-005-0323-7

Cited by 30 publications

(21 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The exact validation process used may be different as well. For instance, we used 10-fold cross validation, while Kaminskj and Czaszejko [21] and others used leave-one-out. Paired with a good performance level, the feature dimensionality of our approach is relatively low with the selected feature sets having less than or around 20 dimensions.…”

Section: Discussionmentioning

confidence: 99%

“…Livshin and Rodet [19] used 62 features and selected the best 20 for real-time solo detection. Kaminskj and Czaszejko [21] used 710 dimensions after PCA. In our study, a 5-dimension set after PCA can also achieve a good classification accuracy.…”

Section: Discussionmentioning

confidence: 99%

“…Misclassifications occurred mainly within each instrument family (woodwinds, brass, and strings). A more recent study by Kaminskyj et al [21] dealt with isolated monophonic instrument sound recognition using k-NN classifiers. Features used include MFCC, constant Q transform spectrum frequency, Root mean square (RMS) amplitude envelop, spectral centroid, and multidimension scaling analysis trajectories.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A Study on Feature Analysis for Musical Instrument Classification

Deng

Simmermacher²,

Cranefield

2008

IEEE Trans. Syst., Man, Cybern. B

102

View full text Add to dashboard Cite

The Department of Information Science is one of seven departments that make up the School of Business at the University of Otago. The department offers courses of study leading to a major in Information Science within the BCom, BA and BSc degrees. In addition to undergraduate teaching, the department is also strongly involved in postgraduate research programmes leading to MCom, MA, MSc and PhD degrees. Research projects in spatial information processing, connectionist-based information systems, software engineering and software development, information engineering and database, software metrics, distributed information systems, multimedia information systems and information systems security are particularly well supported.The views expressed in this paper are not necessarily those of the department as a whole. The accuracy of the information presented in this paper is the sole responsibility of the authors. CopyrightCopyright remains with the authors. Permission to copy for research or teaching purposes is granted on the condition that the authors and the Series are given due acknowledgment. Reproduction in any form for purposes other than research or teaching is forbidden unless prior written permission has been obtained from the authors. CorrespondenceThis paper represents work to date and may not necessarily form the basis for the authors' final conclusions relating to this topic. It is likely, however, that the paper will appear in some form in a journal or in conference proceedings in the near future. The authors would be pleased to receive correspondence in connection with any of the issues raised in this paper, or for subsequent publication details. Please write directly to the authors at the address provided below. (Details of final journal/conference publication venues for these papers are also provided on the Department's publications web pages: http://www.otago.ac.nz/informationscience/pubs/). Any other correspondence concerning the Series should be sent to the DPS Coordinator.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Study on Feature Analysis for Musical Instrument Classification

Deng

Simmermacher²,

Cranefield

2008

IEEE Trans. Syst., Man, Cybern. B

102

View full text Add to dashboard Cite

show abstract

“…Kaminskyj and Nielsen [6,7] have used MFCC in a broad series of instrument classification studies. It was demonstrated that, the MFCC based feature scheme gives the best classification performance [4].…”

Section: Feature Extraction and Evaluationmentioning

confidence: 99%

“…Another study on taxonomic feature analysis for recognition of classical instruments was described by Deng et al [4]. Though the MFCC of music sound have been proved helpful more than once in the instrument timbre classification [6][7][8], little has been progressed in improving the accuracy rate [8,9]. In general, most classifiers are established on a highly redundant feature set [2,4] instead of an individual feature.…”

Section: Introductionmentioning

confidence: 99%

Music Instrument Classification using Nontonal MFCC

Wu¹,

Wang²,

Liu³

2017

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

View full text Add to dashboard Cite

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.

show abstract

Signal Processing Methods for Music Transcription

Klapuri¹,

Davy²

2006

257

View full text Add to dashboard Cite

Automatic Recognition of Isolated Monophonic Musical Instrument Sounds using kNNC

Cited by 30 publications

References 12 publications

A Study on Feature Analysis for Musical Instrument Classification

A Study on Feature Analysis for Musical Instrument Classification

Music Instrument Classification using Nontonal MFCC

Signal Processing Methods for Music Transcription

Contact Info

Product

Resources

About