Academic Journals Database
Disseminating quality controlled scientific knowledge

Musical Instrument Recognition using Spectrogram and Autocorrelation

Author(s): Sumit Kumar Banchhor | Arif Khan

Journal: International Journal of Soft Computing & Engineering
ISSN 2231-2307

Volume: 2;
Issue: 1;
Start page: 1;
Date: 2012;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Speech/music classification | audio segmentation | spectrogram | autocorrelation.

Traditionally, musical instrument recognition ismainly based on frequency domain analysis (sinusoidal analysis,cepstral coefficients) and shape analysis to extract a set ofvarious features. Instruments are usually classified using k-NNclassifiers, HMM, Kohonen SOM and Neural Networks.Recognition of musical instruments in multi-instrumental,polyphonic music is a difficult challenge which is yet far frombeing solved. Successful instrument recognition techniques insolos (monophonic or polyphonic recordings of singleinstruments) can help to deal with this task.We introduce an instrument recognition process in solorecordings of a set of instruments (flute, guitar and harmonium),which yields a high recognition rate. A large solo database isused in order to encompass the different sound possibilities ofeach instrument and evaluate the generalization abilities of theclassification process. The basic characteristics are computed in1sec interval and result shows that the estimation ofspectrogram and autocorrelation reflects more effectively thedifference in musical instruments.

Tango Jona
Tangokurs Rapperswil-Jona

     Save time & money - Smart Internet Solutions