Musical instrument recognition by pairwise classification strategies

  • Essid S
  • Richard G
  • David B
  • 65


    Mendeley users who have this article in their library.
  • 56


    Citations of this article.


Musical instrument recognition is an important as- pect of music information retrieval. In this paper, statistical pat- tern recognition techniques are utilized to tackle the problem in the context of solo musical phrases. Ten instrument classes from different instrument families are considered. A large sound data- base is collected from excerpts of musical phrases acquired from commercial recordings translating different instrument instances, performers, and recording conditions. More than 150 signal pro- cessing features are studied including new descriptors. Two fea- ture selection techniques, inertia ratio maximization with feature space projection and genetic algorithms are considered in a class pairwise manner whereby the most relevant features are fetched for each instrument pair. For the classification task, experimental results are provided using Gaussian mixture models (GMMs) and support vector machines (SVMs). It is shown that higher recogni- tion rates can be reached with pairwise optimized subsets of fea- tures in association with SVM classification using a radial basis function kernel. Index

Author-supplied keywords

  • Feature selection
  • Gaussian mixture model (GMM)
  • Genetic algorithms
  • Inertia ratio maximization with feature space projection (IRMFSP)
  • Musical instrument recognition
  • Pairwise classification
  • Support vector machine (SVM)

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document


Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free