SVM-Based Automatic Classification of Musical Instruments

Liu, Jing; Xie, Lingyun

doi:10.1109/icicta.2010.64

Cited by 22 publications

(14 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent study explored the efficacy of the SVM on the family identification task for a data set that included non-Western instruments. Liu and Xie (2010) achieved 87 percent accuracy on a set of eight instrument families covering both Western and Chinese instruments.…”

Section: Previous Workmentioning

confidence: 99%

Classification of Musical Timbre Using Bayesian Networks

Donnelly

Sheppard

2013

Computer Music Journal

View full text Add to dashboard Cite

In this article, we explore the use of Bayesian networks for identifying the timbre of musical instruments. Peak spectral amplitude in ten frequency windows is extracted for each of 20 time windows to be used as features. Over a large data set of 24,000 audio examples covering the full musical range of 24 different common orchestral instruments, four different Bayesian network structures, including naive Bayes, are examined and compared with two support vector machines and a k-nearest neighbor classifier. Classification accuracy is examined by instrument, instrument family, and data set size. Bayesian networks with conditional dependencies in the time and frequency dimensions achieved 98 percent accuracy in the instrument classification task and 97 percent accuracy in the instrument family identification task. These results demonstrate a significant improvement over the previous approaches in the literature on this data set. Additionally, we tested our Bayesian approach on the widely used Iowa musical instrument data set, with similar results.

show abstract

Section: Previous Workmentioning

confidence: 99%

Classification of Musical Timbre Using Bayesian Networks

Donnelly

Sheppard

2013

Computer Music Journal

View full text Add to dashboard Cite

show abstract

“…Alicja A. Wieczorkowska et al [5] showed Hornbostel-Sachs method gives better result than articulation method with spectrum and temporal features. Jing Liu et al [6] [9] used higher order statistics to detect and quantify the non-gaussianity and non-linearity of regulated processes or control error variables which the main contributors to the poor performance of many of the control loop. Bicoherence plots and bicoherence index are used to detect non-linearities.…”

Section: Introductionmentioning

confidence: 99%

Musical instrument classification using higher order spectra and MFCC

Kazi¹,

Bhalke²

2015

2015 International Conference on Pervasive Computing (ICPC)

View full text Add to dashboard Cite

Higher order statistics in signal processing plays very important role to extract additional information from signals than second order statistics. This paper used higher order spectra to obtain phase entropy, non-linearity and nongaussianity statistics from musical instrument signals to classify them hierarchically with two different taxonomies.19 western musical instruments with full pitch range have been used for classification. Classification accuracy shows improved result when higher order spectra features are combined with MFCC.

show abstract

“…Jing Liu, Lingyun Xie [7] classified 13 western and 13 Chinese musical instruments using SVM with MFCC features but it does not gives better result for percussion family of both western and Chinese instruments. Peter Somerville and Alexandra L. Uitdenbogerd [2] concluded MFCC with KNN classifier for polyphonic sound gives 80% classification accuracy.…”

Section: Classifiermentioning

confidence: 99%

“…In this the orthogonal basis matrix could be obtained without updating the matrix iteratively, which supervised non negative matrix factorization (NMF) algorithm is unable to do. [7] classified musical instruments with several features. Best classification seen in centroid data across one octave.…”

Section: Introductionmentioning

confidence: 99%